supply, installation & maintenance of automatic number plate

January 2008

Western Freeway Public Transport Lane 1 Confidential

Supply, Installation & Maintenance of Automatic

Number Plate Recognition (ANPR) Equipment

Submitted by:

Date: JANUARY 2008

To: GROUP 5

January 2008


ABSTRACT The Violation Enforcement System (VES) Solution will be provided to GROUP 5 / ETA to accommodate the need for consistent, real-time License Plate Recognition (LPR) for vehicles passing through the Public Transport Lanes. SeeWay is a state-of-the-art vision based recognition system for high-speed (up to 350 KM/H) roadside installations. The system can integrate multiple lanes and multiple cameras per lane into a sophisticated vision-based LPR system that identifies and tracks number plates on vehicles travelling at high speeds. The VES will capture all vehicles entering and exiting the enforcement lanes, storing the vehicle image, license plate if present (front and rear), date, time, lane and video of the event. The software will allow vehicles to be enrolled into an allowed list of public transport vehicles, linking this information to the license plate. If a vehicle is detected which is not allowed to use the lane, this will be recorded and a fine can be issued. If the vehicle is listed in the not allowed list, an alarm will be generated. The average speed of the vehicle will be automatically determined and a fine can be issued if it is over the allowed speed. The following are some of the key areas, which are enhanced with the use of this advanced technology: • Promotion of public over private transport • Safety and Security, including identification of stolen vehicles • Safe trip in-vehicle, with on-line traffic reports direct to vehicle • Limit traffic delays associated with unexpected events • Provide effective signage and provide better road user services • Increase traffic capacity, including real time flow estimation • Empowerment • Training and support The financial offering for the advanced LPR ASD solution is provided as a capital amount of R1, 994, 713.15, including install between the 1st of February and 1st of March 2008, high level training for 4 users at the start and 1 day a month thereafter, comprehensive maintenance and 4 hour response and support for a year.

January 2008


The Supply, Installation & Maintenance of Automatic Number Plate Recognition (ANPR) Equipment field systems employ the same SeeCar OCR engine, which will run on the local processing units. The OCR engine processes images, locates the relevant license plate ID in the image, and produces an alphanumeric result for each image processed. The OCR engine is based on neural network technology and can be trained to recognize different fonts, characters and syntax. In SeeWay systems there is a need to guarantee an absolute up time, i.e. the systems always work, even in case of malfunction or required service. The system is designed to work in an automatic redundancy mode, where a 2nd server automatically takes over the functions of the other down server. The dual servers can be set to monitor each other through network messaging and revert to degraded mode if there is a fault in one of the servers. The design of the system allows for both front and rear plate capture and an additional overview colour image and video of the vehicle. Each LPR unit reports the vehicle recognition events via TCP/IP network messages to a central computer in the traffic control room. The central computer application reads the recognition results from all sites, calculates the travel data (in real-time), and displays it to the operator or writes this to a log. Using outputs of several sites, a back end program is used to calculate the average speed of the vehicles, based on the time of journey. The system is used world wide for various applications, including toll roads, monitoring, and average speed and car flow studies. The development of LPR started in 1995 and first systems were installed internationally in 1996/7. The first systems were deployed in RSA in 1999 and the years experience in LPR within SA is over 15 years. Numerous reference sites are detailed, including the existing N3 site in the Midlands, the M4 Durban example, N3 (Ashburton to Camperdown) where the distance between the two points was 13.750 KM, etc. A CD is included with extensive presentations, demos, circuit and wiring diagrams, user and install manuals, additional site information, product details to be utilised, including the LPR, ASD and utilities software (see monitor, see cleaner, see service and see cleaner).

January 2008


Table of Contents: ABSTRACT Table of Contents

Definitions, acronyms and abbreviations

INTRODUCTION Overview System description: System Architecture

SITE LOCATION SeeWay Layout: Installation & Triggering

AVERAGE SPEED DETERMINATION System Architecture: Overview LPR unit Windows Main Display LPR Client Network System operation: VES Data Output OCR Engine See Data Client-Server Architecture Alarm Generation Possible Database connectivity

SEE CAR FLOW CENTRAL APPLICATION

Overview Travel Map Travel Time tabular display Special vehicles Travel time Status: LPR unit status Travel Time Calculations Travel time Average Travel time Storage and export of Results

System stability Redundancy

REFERENCE SITES: Record of Similar Projects Completed M4 Durban PMB to Durban – N3 from Ashburton to Camperdown

January 2008


REFERENCE SITES: Record of Projects Completed in SA

JAI CAMERAS

JAI Camera Pins Description IPort PT1000-CL IP Engine Theory of operation

HARDWARE Components description Pulsed Illumination unit I/O Card Terminal Block (TBL): See Way Schematic Diagram Camera Settings Video flow Transaction number

ASD KEY COMPANY PERSONAL PROFILE

Barry Fryer Dudley CEO CURRICULUM VITAE : Dr. M. F. MITCHELL, CHAIRMAN

Seeway software Cabinet door signalling device Vehicle single channel detector Support Software maintenance Spares Delivery period - Guarantee - Training OPTIONS: LINK TO SAPS STOLEN VEHICLE DATABASE Tsohle-Unicode Vehicle Information Systems

Financial Offering: Capital amount

APPENDIX: ADDITIONAL ASD INFO:

APPENDIX 1 ASD for Ethekwini Traffic Authority APPENDIX 2 See Way Manual APPENDIX 3: Overview APPENDIX 4: See Lane APPENDIX 13: ASD - LPR Solution for 3 sites 6 lanes

January 2008


MANUALS APPENDIX 5: “See Car DLL APPENDIX 6: See Data APPENDIX 7 See Lane Install APPENDIX 8 See Utilities APPENDIX 9 See Lane Manual APPENDIX 10 Installing Pleora software + Giga card

SA REFERENCE SITES

APPENDIX 11: “ASD N3 RESULTS Sat Jan 06th APPENDIX 12: “ASD N3 RESULTS SUN JAN 7th APPENDIX 14 IT WEB ASD Article 31 Oct 2006 - N3 ASHBURTON images - See Car Speed Demo - I-CUBE LPR Demo of RSA Customised Plates - N3 Camperdown Player EX - Hand Held Plate Demo - Colour LPR_Demo - DBN Metro CCTV Control Room

SOFTWARE

Drivers: Hasp Drivers: IO Card Drivers: Pleora Drivers SEEWAY: Seeway SEEWAY: Documents SEEWAY: Tools – SeeCal SEEWAY: Tools – See Cleaner SEEWAY: Tools – See Monitor SEEWAY: Tools – See Service SEEWAY: Client Applications SEEWAY: Client Applications – See Lane Log SEEWAY: Client Applications – See Speaker

PRODUCT SPECIFICATIONS APPENDIX 14 Nortec TD 136 APPENDIX 15 AXIS IP camera APPENDIX 16 AXIS 223M Network Camera APPENDIX 16 HSDPA_WirelessRouter APPENDIX 17 Edge_Router-230M APPENDIX 18 Laser Vehicle Detector APPENDIX 19 Quickbridge APPENDIX 19 Switch APPENDIX 20 UPS

TO BE PROVIDED BY CLIENT

January 2008


LIST OF FIGURES Figure 1 Site Items Required ................................................................................... 11 Figure 2 Elements making up SeeWay .................................................................... 12 Figure 3 SeeWay Connectivity ................................................................................ 13 Figure 4 Site locations and components ................................................................... 14 Figure 5 Overview of the 3 sites in relation to ETA servers ..................................... 14 Figure 6 Sign Gantry at WaterFall Rd, Eastbound Lane Front Camera View ........... 15 Figure 7 Sign Gantry at WaterFall Rd, Eastbound Lane Rear Camera View ............ 15 Figure 8 Sign Gantry at WaterFall Rd, Westbound Lane Front Camera View .......... 16 Figure 9 Sign Gantry at WaterFall Rd, Westbound Lane Rear Camera View ........... 16 Figure 10 Tollgate Road Bridge, Eastbound Lane Front Camera View .................... 17 Figure 11 Tollgate Road Bridge, Eastbound Lane Rear Camera View ..................... 17 Figure 12 Tollgate Road Bridge, Westbound Lane Front Camera View ................... 18 Figure 13 Tollgate Road Bridge, Westbound Lane Rear Camera View .................... 18 Figure 14 Essenwood Road Bridge, Eastbound Lane Front Camera View................ 19 Figure 15 Essenwood Road Bridge, Eastbound Lane Rear Camera View ................. 19 Figure 16 Essenwood Road Bridge, Westbound Lane Front Camera View .............. 20 Figure 17 : Essenwood Road Bridge, Westbound Lane Rear Camera View ............ 20 Figure 18 Rear camera and Site PC layout ............................................................... 22 Figure 19 Rear camera wiring and layout ................................................................ 22 Figure 20 Layout for a rear camera .......................................................................... 23 Figure 21 Distance measurements for front camera install ....................................... 23 Figure 22 LPR unit Architecture .............................................................................. 26 Figure 23 Personalised Plates are recognised using LPR .......................................... 28 Figure 24 Rear LPR capture and recognition with alarm .......................................... 33 Figure 25 Log of the data and images from each site ............................................... 34 Figure 26 Possible database connections required .................................................... 35 Figure 27 Typical Site Layout showing database links ............................................. 35 Figure 28 Settings in the ASD software ................................................................... 40 Figure 29 Example of the results of ASD ................................................................. 40 Figure 30 Trucks speeding on the M4 towards the airport ........................................ 42 Figure 31 Visitors to Durban who obey the rules of the road ................................... 43 Figure 32 M4 Durban Demo of ASD ....................................................................... 43 Figure 33 Ashburton on the N3 ............................................................................... 44 Figure 34 Camperdown on the N3 ........................................................................... 44 Figure 35 Average Speed Determination created from 2 sites on the N3 .................. 45 Figure 36 Pin layout ................................................................................................ 60 Figure 37 Image Characterises from the JAI camera used in SeeWay ...................... 60 Figure 38 IP engine interfaces JAI cameras, transfers images over Gigabit link. ...... 61 Figure 39 Pulsed IR illumination ............................................................................. 64 Figure 40 Wiring for the Illumination Units ............................................................. 64 Figure 41 Setting Page............................................................................................. 78 Figure 42 LPR Recognition .................................................................................... 104 Figure 43 ASD on the N3 ....................................................................................... 105 Figure 44 ASD PROJECT PLAN ........................................................................... 111

January 2008


Definitions, acronyms and abbreviations AGC -Automatic Gain Control - A circuit for automatically controlling amplifier gain in order to maintain a constant output voltage with a varying input voltage within a predetermined range of input-to-output variation Aperture - In television optics, it is the effective diameter of the lens that controls the amount of light reaching the photoconductive or photoemitting image pickup sensor. Aspect Ratio - The ratio of width to height for the frame of the televised picture 4:3 for standard systems, 5:4 for 1K x 1K, and 16:9 for HDTV Automatic Brightness Control - In display devices, the self-acting mechanism which controls brightness of the device as a function of ambient light. Automatic Gain Control - A process by which gain is automatically adjusted as a function of input or other specified parameter. Automatic Iris Lens - A lens that automatically adjusts the amount of light reaching the imager. Automatic Light Control -The process by which the illumination incident upon the face of a pickup device is automatically adjusted as a function of scene brightness Bandwidth - The number of cycles per second (Hertz) expressing the difference between the lower and upper limiting frequencies of a frequency band; also, the width of a band of frequencies Blooming - The defocusing of regions of the picture where the brightness is at an excessive level, due to enlargement of spot size and halation of the fluorescent screen of the cathode-ray picture tube. In a camera, sensor element saturation and excess which causes widening of the spatial representation of a spot light source. Brightness - The attribute of visual perception in accordance with which an area appear to emit more of less light. (Luminance is the recommended name for the photo-electric quantity which has also been called brightness.) CCD - See Charge Coupled Device C Mount - A television camera lens mount of the 16 mm format, 1 inch in diameter with 32 threads per inch. CCTV - Common abbreviation for Closed-Circuit Television Charge-Coupled Device CCD - For imaging devices, a self-scanning semiconductor array that utilizes MOS technology, surface storage, and information transfer by shift register techniques. Contrast - The range of light to dark values in a picture or the ratio between the maximum and minimum brightness values. Contrast Range - The ratio between the whitest and blackest portions of television image DDE – Dynamic Data Exchange Depth of Field - The in-focus range of a lens or optical system. It is measured from the distance behind an object to the distance in front of the object when the viewing lens shows the object to be in focus. Depth of Focus -The range of sensor-to-lens distance for which the image formed by the lens is clearly focused. DLL – Dynamic Linked Library EPS - Edge pre-select Fiber Optics - Also called optical fibers or optical fiber bundles. An assemblage of transparent glass fibers all bundled together parallel to one another. The length of each fiber is much greater than its diameter. This bundle of fibers has the ability to transmit a picture from one of its surfaces to the other around curves and into otherwise inaccessible places with an extremely low loss of definition and light, by a process of total reflection. Field - One of the two equal but vertically separated parts into which a television frame is divided in an interlaced system of scanning. A period of 1/60 second separates each field start time.

January 2008


Field of View - The maximum angle of view that can be seen through a lens or optical instrument. Focal Length - Of a lens, the distance from the focal point to the principal point of the lens Focal Plane - A plane (through the focal point) at right angles to the principal point of the lens Focal Point - The point at which a lens or mirror will focus parallel incident radiation. Gbps – Giga Bits per second HTS – Hi-Tech Solutions Iris - An adjustable aperture built into a camera lens to permit control of the amount of light passing through the lens. IO – Input output IP – Internet Protocol IR – Infra Red JPG – Joint Photographic Group Image Format LED – Light Emitting Diode Monitor - A unit of equipment that displays on the face of a picture tube the images detected and transmitted by a television camera. MSMQ – Microsoft Message Queue ND Filter - A filter that attenuates light evenly over the visible light spectrum. It reduces the light entering a lens, thus forcing the iris to open to its maximum. Patch Panel - A panel where circuits are terminated and facilities provided for interconnecting between circuits by means of jacks and plugs. PC – Windows based Personal Computer Pixel - Short for Picture Element A pixel is the smallest area of a television picture capable of being delineated by an electrical signal passed through the system of part thereof. The number of picture elements (pixels) in a complete picture, and their geometric characteristics of vertical height and horzontal width, provide information on the total amount of detail which the raster can display and on the sharpness of the detail, respectively. PWC - pulse width control RFID – Radio Frequency Identification Shutter - Ability to control the integration (of light) time to the sensor to less than 1/60 second; e.g: stop motion of moving traffic. Signal-to-Noise Ratio - The ratio between useful television signal and disturbing noise or snow Snow - Heavy random noise. Spike - A transient of short duration, comprising part of a pulse, during which the amplitude considerably exceeds the average amplitude of the pulse. TCP – Transmission Control Protocol TBL – Terminal Block Test Pattern - A chart especially prepared for checking overall performance of a television system. It contains various combinations of lines and geometric shapes. The camera is focused on the chart, and the pattern is viewed at the monitor for fidelity. VB – Visual Basic VDC – Voltage Direct Current Vertical Resolution - The number of horizontal lines that can be seen in the reproduced image of a television pattern VES – Vehicle Enforcement System Zoom - To enlarge or reduce, on a continuously variable basis, the size of a televised image primarily by varying lens focal length. Zoom Lens - An optical system of continuously variable focal length, the focal plane remaining in a fixed position.

January 2008


INTRODUCTION

Overview The Violation Enforcement System (VES) Solution will be provided to Group 5 to accommodate the need for consistent, real-time License Plate Recognition (LPR) for vehicles passing through the Public Transport Lanes. The system, referred to as the VES, will interface with a list of allowed public transport vehicles to provide a take-and-discard methodology for the vehicles’ video and license plate data. Vehicles using the lanes which are speeding (either public transport vehicles or not), determined by Average Speed between two of any of the 3 points (A to B, B to C or A to C) will generate an alarm, allowing proactive, real time reaction or a fine to be generated. The road side portion of the solution proposed is called SeeWay. The VES will allow the Transport Authority to

- improve safety on roads and eliminate “black spots”; - limit road closures and traffic delays associated with road works and

unexpected events; - manage the flow of traffic to minimise delays; - provide effective signage of real time events as they occur; - increase traffic capacity; - provide better road user services such as information signs and systems.

SeeWay is a state-of-the-art vision based recognition system for high speed Roadside installations. The system can integrate multiple lanes and multiple cameras per lane into a sophisticated vision-based License Plate Recognition (LPR) system that identifies and tracks number plates on vehicles travelling at high speeds. The system is used world wide for various applications, including Toll Roads, monitoring, average speed and car flow studies. The application is supported by a full set of optical and hardware sub-systems as well as software applications and utilities. The system will work to detect and capture the license plate information for every vehicle passing through the enforcement lanes. It will be the responsibility of the laser detectors to determine vehicle presence, via the laser detectors digital outputs. When vehicle presence is determined, a solid state relay will be set HIGH for approximately 1ms. The VES Cameras will then capture a set of images, process these and output the best image and the resulting license plate, lane, time and associated data to the network. The servers will capture the data for further processing as required. Average Speed – using outputs of several sites, a back end program is used to calculate the average speed of the vehicles, based on the time of journey. The average speed can be used for:

- Enforcement (speed violation). The average speed is used to issue violation tickets.

January 2008


- Flow estimation – the average speed and time of journey can be used for road conjunction analysis that can assist traffic planning.

- On-line traffic report – the roadside information can be reported on web sites in order to supply live reports from the freeway.

- Monitoring – the recognition information may be used for various security applications.

The following are some of the areas which are enhanced with the use of this advanced technology:

• Promotion of public over private transport • Safety and Security • Safe trip in-vehicle • Technological • Adequate skills and resources • Adequate maintenance • Empowerment • Training and support

System description: The proposed system consists of 2 enforcement lanes, in and out of Ethekwini, with multiple cameras monitoring the entrance, middle and exit of each lane. Each camera is connected to an IP switch which allows any of the connected computers to view and process the data obtained from the vehicle. If any of the cameras goes down, an alarm is generated immediately. The front black and white cameras, with pulsed IR to overcome the head lights are supported by rear colour cameras, performing both license plate recognition and capturing vehicle colour and a video of the incident. This video is used for verification when drivers claim outside events forced them into the enforcement lane. If any of the computers fail, the other computers automatically take over the processing of the cameras attached to that computer.

Contract No. IT 1842: Site Specific Items

Location

See Way Camera 11.5-69

Assy

CONT.ILL. WAY IR 1000

Assy

Colour Capture camera

IP 65 housing with 2

computersCamera

Poles

1 Channel Vehicle detector

SMC 8508T 8 PORT 1G

UPS (4 hrs)

SeeWay Two- Lane System

Surge Protection

Essenwood Road Bridge 1 2 1 1 2 2Eastbound Lane 1 2 1 2Westbound Lane 1 2 1 2

Tollgate Road Bridge 1 2 1 1 2 2Eastbound Lane 1 2 1 2Westbound Lane 1 2 1 2

Sign Gantry at WaterFall Rd 1 1 1Eastbound Lane 1 2 1 2 2 2 2Westbound Lane 1 2 1 2

TOTAL 6 12 6 3 6 12 3 3 6 6 Figure 1 Site Items Required All vehicles passing the camera will be recorded in terms of the time, lane, direction, license plate (if present), automatic detection of unauthorized vehicles, an alarm if the vehicle is wanted (black list) and other database operations.

January 2008


System Architecture SeeWay is a turn-key system comprises of the following elements: • PC running Windows XP Pro • SeeCar DLL - which is used to analyze the images and extract license plate string • 1-3 Recognition Camera unit(s) to capture the images. These cameras are high resolution state of the art cameras that are connected to the PC via a gigabit network. • Gigabit Network – 8-port switch and network card (or motherboard network). This is an internal network used for communicating with the cameras. Note: An additional 100Mb/1Gb network connection is required in order to report the result to external systems.

Figure 2 Elements making up SeeWay • Illumination units to illuminate the plates. The illumination units may be external lights, or solid state strobe units that are supplied by I-Cube. • I/O card – input/output board with multiple I/O discrete lines. This board supports the sensors and illumination control. It is connected via a cable to a terminal interface board with easy connections and indicator lights. • Colour overview camera – used as an option to supply colour images and video used for archiving. This is used for additional recognition where no front plate is present. • Laser Sensors to indicate the presence of the car (a sensor for each lane) • SeeWay - The SeeWay Windows application interfaces the hardware elements (camera/illumination unit(s), IO card and sensor). It controls the illumination, reads the video inputs and passes the images to the DLL in order to obtain the recognition results. The application displays the image and recognition results. It then exports the results

January 2008


using messages and image files. Its man-machine interface supports on-line setting control, which can easily adapt the application to various types of configurations. The image below illustrates how the items link together on site and in the control room. All the items indicated in the image below reside on site, except for the remote database which will be on the central server in the control room.

Block Diagram A breakdown of the SeeWay system is shown in the following illustration, which shows a typical configuration of a SeeWay LPR system (single lane). Although a monitor is shown, it is optional, and a remote access thru the network is usually the standard configuration.

Figure 3 SeeWay Connectivity The SeeWay application runs as a background Windows application in the PC (in the centre), which has a gigabit network connection (from a network card or the motherboard), via a Gigabit switch to the IP recognition camera(s) (with integrated illumination). The number of these high resolution cameras depends on the width and number of lanes, but is limited to 3 or less cameras based on traffic volume. The PC has an I/O card which is connected via a terminal block to the sensors and the illumination control signals. An option of a colour overview picture and video is available with a colour overview camera.

January 2008


SITE LOCATION Three sites on the N3 have been identified.

Contract No. IT 1842: Site Information

Location Image Sign No No of Lanes Traffic DirectionLane Width

Cameras Per Lane

Colour Cameras

Black and White

Cameras

Essenwood Road BridgeEastbound Lane E1 TBA 1 E 3.2 2 1 1Westbound Lane E2 TBA 1 W 3.2 2 1 1

Tollgate Road BridgeEastbound Lane T1 TBA 1 E 3.2 2 1 1Westbound Lane T2 TBA 1 W 3.2 2 1 1

Sign Gantry at WaterFall RdEastbound Lane W1 TBA 1 E 3.2 2 1 1Westbound Lane W2 TBA 1 W 3.2 2 1 1

TOTAL 6 0 6 0 12 6 6 Figure 4 Site locations and components

Figure 5 Overview of the 3 sites in relation to ETA servers

January 2008


Site 1: Sign Gantry at WaterFall Rd, Eastbound Lane Front Camera View 29 50’ 29.74 S 30 58’52.42” E

Figure 6 Sign Gantry at WaterFall Rd, Eastbound Lane Front Camera View Please note: This will be a BW image, zoomed in for the plate detection specifically, not a colour image. This image is provided as an illustration only. Site 1: Sign Gantry at WaterFall Rd, Eastbound Lane Rear Camera View 29 50’ 29.46 S 30 58’51.74”

E Figure 7 Sign Gantry at WaterFall Rd, Eastbound Lane Rear Camera View

January 2008


Site 1: Sign Gantry at WaterFall Rd, Westbound Lane Front Camera View 29 50’ 29.46 S 30 58’51.74” E

Figure 8 Sign Gantry at WaterFall Rd, Westbound Lane Front Camera View Site 1: Sign Gantry at WaterFall Rd, Westbound Lane Rear Camera View 29 50’ 29.74 S 30 58’52.42” E

Figure 9 Sign Gantry at WaterFall Rd, Westbound Lane Rear Camera View

January 2008


Site 2: Tollgate Road Bridge, Eastbound Lane Front Camera View 29 51’ 01.32 S 30 59’25.72” E

Figure 10 Tollgate Road Bridge, Eastbound Lane Front Camera View Site 2: Tollgate Road Bridge, Eastbound Lane Rear Camera View 29 51’ 01.16 S 30 59’24.79” E

Figure 11 Tollgate Road Bridge, Eastbound Lane Rear Camera View Please note: This image is provided as an illustration only, the camera will be position in the median, behind the car and not as illustrated above.

January 2008


Site 2: Tollgate Road Bridge, Westbound Lane Front Camera View 29 51’ 01.16 S 30 59’24.79” E

Figure 12 Tollgate Road Bridge, Westbound Lane Front Camera View Site 2: Tollgate Road Bridge, Westbound Lane Rear Camera View 29 51’ 01.32 S 30 59’25.72” E

Figure 13 Tollgate Road Bridge, Westbound Lane Rear Camera View Please note: This image is provided as an illustration only, the camera will be position in the median, behind the car and not as illustrated above.

January 2008


Site 3: Essenwood Road Bridge, Eastbound Lane Front Camera View 29 51’ 08.12 S 30 59’49.45” E

Figure 14 Essenwood Road Bridge, Eastbound Lane Front Camera View Please note: This will be a BW image, zoomed in for the plate detection specifically, not a colour image. These images are provided as an illustration only. Site 3: Essenwood Road Bridge, Eastbound Lane Rear Camera View 29 51’ 07.83 S 30 59’48.67” E

Figure 15 Essenwood Road Bridge, Eastbound Lane Rear Camera View

January 2008


Site 3: Essenwood Road Bridge, Westbound Lane Front Camera View 29 51’ 07.83 S 30 59’48.67” E

Figure 16 Essenwood Road Bridge, Westbound Lane Front Camera View Site 3: Essenwood Road Bridge, Westbound Lane Rear Camera View 29 51’ 08.12 S 30 59’49.45” E

Figure 17 : Essenwood Road Bridge, Westbound Lane Rear Camera View

January 2008


Introduction HTS products are uniquely suited to harsh environments, including poor weather and lighting conditions. Our Neural Network Technology and unique image processing provides both digital and video image records, for an easily operable, “seeing is believing” customer experience. Hi-Tech Solutions proprietary software products support our image processing products and provide a highly user-friendly interface. SeeWay License Plate Recognition systems detect and read vehicle license plates for traffic surveillance, law enforcement, parking, access control, traffic, and security applications. The number plate recognition is available as a complete system which is based on a background Windows application, Windows DLL or Linux library, as a stand-alone turn-key version, or as different special-task systems. Successful applications include law enforcement, surveillance, felon searches, toll road collection, parking facilities and site access control.

Our system has the following advantages over other mechanical and automated solutions:

• Simple configuration • Fast response (output in milliseconds) • High recognition rate • Accurate and reliable under variable ambient conditions • 24 hour operation • User friendly display and operation • Simple integration into the existing computer resources • Collects traffic history data • Provides view of the lane traffic • Cost-effective The following pages provide a detailed description of our proposal, scope of supply, and general commercial terms of our proposal. General technical material describing the system, its components and its performance can be found in the SeeWay

Technical Information Document in the appendix section of this proposal.

Application Description The Western Freeway Project is intended to monitor Public Transport Lanes. These lanes are solely for the use of Public Transport vehicles. Any other vehicle using these lanes will be fined. The Tender requires a sophisticated image processing system that tracks vehicle number plates, reads and identifies their numbers, report violations (non public transport vehicles). It is intended for high speed lanes, up to 200 KM/H.

January 2008


SeeWay Layout: Installation & Triggering The design of the system allows for both front and rear image capture. The rear camera will capture the rear–license plate images of every vehicle detected. An additional recognition is desired in order to increase the recognition coverage (a dual camera per lane installation). For each trigger a series of images will be captured. The images will then be automatically reviewed by the application running on the Lane Controller, and the best result will be selected among all identifications. The application will also select the best image to be reported that will contain the plate image. Once a result is determined, the data will be sent by a message to the ETA server. Below is a diagram depicting the physical layout of the equipment involved in the single-lane SeeWay VES system (only the rear camera is shown):

Figure 18 Rear camera and Site PC layout

Figure 19 Rear camera wiring and layout The effective field of view of each unit is about 2.7-3.5 meters in order to achieve the proper plate size. A rear plate installation is shown in the following diagram – for the case where the camera is installed on the side. The SCH (SeeCarHead camera /

January 2008


illumination unit) is mounted at the side of the lane as close as possible to the edge (parameter C) and at height of about 1.1 meters. The range (parameter B in the figure) is 5.5 meters from the “loss of detection” point (where the rear of the vehicle leaves the detector) using a 16 mm lens.

Figure 20 Layout for a rear camera The following illustration shows a typical layout of the SeeWay solution (Front Camera only):

Figure 21 Distance measurements for front camera install

January 2008


In this case the detector should be defined in settings (see the Install Manual) as active when the vehicle leaves the detection zone (“Normally Closed”). This also can be arranged by selecting the normally closed outputs of the loop detector. This is since the proper point of starting the images capturing is when the rear of the car leaves the detection line – in order to avoid the effect of the length of the car. The SCH unit should be installed at about 5.5M from the loop detection line for standard lens. See the illustration above, parameter B. This translates to about 9 meters or more from the front of the car (for standard lens) since a typical vehicle is about 4 meters. The side distance (parameter C) in this installation is identical – 0.0 to 0.5 meters. Side of the Traffic lane: Install the SCH as close as possible to the traffic lane, within 0.0 to 0.5 meters. See the illustration above, parameter C. Distance from loop – Dual Camera per lane (Stereo): The SeeWay application can operate in dual camera per lane ("Stereo" mode). In this mode two cameras are used to recognize the car, thus increasing the recognition rate. The application uses special logic that takes both results in consideration before sending the car plate number.

SeeWay can be configured with 2 separate sensors, or even set to take pictures from both cameras at the same detection time on the same loop event. However, the recommended configuration is to share a single sensor using front and rear cameras. In this single-loop mode it is configured to activate the front camera at the rise of the sensor signal and activate the rear camera at the fall of the sensor signal. Thus, the length of the vehicle will not affect the results. The installation procedure is identical for installing front and rear plates as described in the previous paragraphs. This single-loop stereo mode is illustrated in the above illustration. The typical values are A front = 6.5 meters and A rear = 5 meters for standard lens (or A front= 5).

January 2008


AVERAGE SPEED DETERMINATION The following illustration shows one of the sites (“Site A” out of N sites) monitored by a License Plate Recognition (LPR) unit. Each unit is connected via a network to a control room. Each LPR unit transmits its recognition results to the control room computer where the data is collected and analyzed. The central computer application then updates and displays the traffic status that includes average journey times between the LPR sites and also traffic flow statistics. This information is presented in real-time and saved to a traffic database for off-line processing.

SeeCarFlow illustration (Site A of N sites, with control room)

System Architecture: Overview

The system is based on Vehicle License Plate Recognition (LPR) stand-alone systems. Multiple LPR units are installed at several permanent sites (6) located in selected urban road routes (N3) in the city. Each LPR system performs real-time recognition on passing cars in a single traffic lane. The LPR unit is based on a Windows application that controls its integrated camera/illumination unit and an LPR recognition engine.

Each LPR unit reports the vehicle recognition events via TCP/IP network messages to a central computer in the traffic control room. The central computer application reads the recognition results from all sites, calculates the travel data (in real-time), and displays it to the operator.

January 2008


This section describes each of the major elements.

LPR units Each LPR unit is a turnkey system, which is comprised of the following elements:

• a PC Pentium running Windows XP

• LPR unit Windows application software package (described below)

• Recognition DLL – the recognition engine which is used to analyze the images and extract license plate string

• Camera/ Illumination unit to capture the images (detailed below)

• a I/O card - multiple I/O discrete lines - which supports the sensors, illumination control and optional gate-open signal.

• Laser sensor to indicate a presence of the car (the description is provided below)

• a list of known vehicles (such as buses or taxis) which will be analyzed separately in the traffic analysis

These components are shown in the following illustration.

Camera/Illumination PC Frame Grabber Recognition DLL

Sensor Illum. control LPR Windows application ID strings Identified Vehicle

I/O CARD

Figure 22 LPR unit Architecture

When a vehicle triggers the sensor, the LPR application activates the illumination (which is controlled by the IO card) and captures a series of images (one or more image fields) which are captured by the frame grabber. It then proceeds with the identification of the car.

The LPR system is designed to work simultaneously with one to six traffic lanes. However in the SeeCarFlow system the traffic load will limit the number of lanes. According to the traffic load for each location it will be determined if a single or double lane will be assigned for each PC.

January 2008


The application also reports on special vehicles that are listed in the ‘white-list’ (listed in a file, cars.txt). This is used in SeeCarFlow application to differ between standard vehicles and special vehicles when displaying the results.

LPR unit Windows Main Display The LPR unit application main window is designed to display as much information as possible in a friendly user interface. The window is divided into several display panes, where each pane is responsible for a single system task (video images, system status, identified code, ...). The different panes include: - Image Display - shows video from the camera (from one of the lanes) - History Log - display a list of all identified vehicles - Identification Window - a graphical representation of the identified vehicle - Status Window - system messages and sensor status display An example of such display is shown in the following figure. The vehicle (that is shown) was captured with a front camera/illumination unit and displayed on the image display; its license plate number is shown in the bottom list and graphical display.

Example of LPR application main view The application can operate automatically without operation control and can be minimized to a background application. For more details – see the SEEWAY MANUAL

January 2008


Figure 23 Personalised Plates are recognised using LPR

LPR Client The LPR unit application is designed to share the vehicle identification results with other processes. This can be done either by external communication (RS232) or by application-to-application messages. The latter method is implemented by DDE messages that are sent after each identification cycle. Each vehicle generates one message containing the recognition result.

When a vehicle triggers the sensor, the LPR unit application captures a series of images (one or more), then proceeds with the identification of the car. After completing the identification cycle, a DDE message containing the ID is sent to the PC Windows system (along with more information: date and time, lane number, ‘white-list’ vehicle and image pointer).

This message is intercepted by another application - the LPR client process. This process receives the messages, groups a series of recognition results together (for reducing the network bandwidth requirements) and sends the recognition block across the network via TCPIP. This data is received at the control room by the SeeCarFlow central application and used for traffic processing.

January 2008


Camera/Illumination PC Frame Grabber Recognition DLL

Sensor LPR unit application Identified Vehicle

I/O CARD DDE Message with ID

Client process

TCP/IP

Other Sites SeeCarFlowCentral

Data flow of the Recognition results

Network The sites will be connected together by a network. The recognition results (grouped in a block consisting of several recognition results) are transmitted over the network The TCP/IP protocol is used for this transmission. Each of the Client applications will be a server in this network, and connect to the client (the central application).

Networked LPR Sites

January 2008


Each of the Client/Server applications has a configurable list of TCP/IP addresses that specify the network connections. Adding a new site is simple so the traffic control system is easy to expand. The information sent across the network includes also the system status in each site for on-line diagnostic status display. Additional activities are possible through this network by maintenance technicians:

• change of configuration parameters settings • software update • update of list of known (allowed) vehicles • Other applications as required.

System operation: Vehicles identified as being able to use the public transport lane would be enrolled into a database. This database would be stored on the central servers and mirrored on the local computers. When a vehicle that is allowed to use the lane passes the camera, notification of that vehicle would be generated, along with any other required information, such as driver name or taxi association or type of vehicle etc. The database could be generated from:

- Existing Databases of busses and taxis, such as eNATIS, Durban Metro Database, etc.

- Driver enrolment via SM, E-Mail, phone, web site etc. - Uses of the system, that is when a vehicle is detected using the lane it could be

then the enrolled into the allowed database. - Any other existing or future data source as required.

The VES will capture all vehicles entering and exiting the enforcement lanes, storing the vehicle image, license plate if present, date, time, lane and image. The software will allow vehicles to be enrolled into an allowed list, linking this information to the license plate. If a vehicle is detected which is not allowed to use the lane, this will be recorded. If the vehicle is in the black list, an alarm will be generated. The average speed of the vehicle will be automatically determined and an alarm generated if it is over the set speed VES Data Output Data will initially be acquired and kept for every vehicle, and ETA will determine which images to keep and which to discard. The data for each vehicle will include: 1) Image - A stand alone, human readable monochrome JPEG image with a resolution of approximately 1380 pixels by 1024 pixels (for SeeWay). This image will display the detected plate on the best recognized image within the set of images that are captured for that event.

January 2008


2) VES Optical Character Recognition Data: • Lane (Site) unique ID integer number • License Plate string • TCS Synchronization Code (for SeeWay only) • Date and Time of Image Capture • File Name (a link to the name of the resulting .jpg file stored in the VES server) • Confidence of the recognition result The data will be transmitted to the TCS in two forms: a) Windows DDE (Dynamic Data Exchange) Message - sent to the ETA server over the TCPIP network. The DDE will contain the VES Optical Character Recognition Data as described above. b) Image file - which will be stored on the VES server, then transmitted to the ETA over the NCS via a dedicated transfer service running on the Trip Processing Server.

OCR Engine All of the systems (3 SeeWay sites of 2 front and 2 rear cameras) employ the same SeeCar OCR engine, which will run on the local processing units. The OCR engine processes images, locates the relevant license plate ID in the image, and produces an alphanumeric result for each image processed. The OCR engine is based on neural network technology and can be trained to recognize different fonts, characters and syntax. The systems supplied for the ETA Project are specially trained to recognize license plates in Southern Africa, and focus on the local South African plates.

January 2008


SEE DATA SeeData is a software service application that connects a cluster of recognition systems (such as SeeLane or SeeWay) together by a network. The networked units can thus report the recognition results to a Central server. Client-Server Architecture SeeData is a set of applications, which comprise of the following elements (see also the following illustration): • Remote units (one or more) - also referred as client nodes, or front end units. Each unit has a LPR (License Plate Recognition) recognition system which generates recognition messages which report the results. • Central server (single) The SeeData application is connected to one or more remote units, and collects their reports to a central recognition system. It is also possible to send commands from the Server to the remote (front-end) recognition units, although this is not described in the diagram.

Events data The SeeData application, which runs on the Central server, communicates with front-end OCR hosts by a protocol designed especially for I-Cube applications. On this protocol the I-Cube recognition systems report the results to the central server. One of the main protocol features is that if SeeData is down (due to an internal error or because of OS issue) each host can accumulate up to 10,000 events. Accumulated events will be delivered when SeeData is available on network again. The SeeData protocol is based on TCP/IP. It allows to SeeData to operate in cross OS environment. For example, SeeData could receive recognition results from Windows (SeeLane for example) and embedded Linux (C4, Compact Car Controller).

January 2008


Images and video clips If “Transfer Images” option is configured in SeeData settings the application will handle the transfer of locally saved images and video clips from the front end hosts to the SeeData Central Server station.

Figure 24 Rear LPR capture and recognition with alarm Recognition data Vehicle topic is used for transmitting of recognition data (SeeData output). Items of the topic are: • CarCode – string contains recognized license plate • Name – string contains driver first and last name as was found in database • Time – event time in format: “Mon Jul 03 14:29:06 2006” • LaneId – string contains lane index (zero based) • Authorized – string “1” (vehicle is authorized) or “0” (not authorized) • File – string contains saved vehicle image path • Confidence – string contains recognition confidence (“0”-“100”) • PlateType – string contains one based index of plate format • Trigger – string contains exact trigger time stamp in format:”032809233”, which means 3 h 28 m 09s 233 ms

January 2008


LOG OF EVENTS

Figure 25 Log of the data and images from each site ALARM GENERATION A list of vehicles which, when captured, will result in an alarm, can be added to the system. Which vehicles are added to the list, who adds them and how they should be removed needs to be determined. The alarm list is stored on the central computer and replicated on each of the field computers.

January 2008


Possible Database connectivity

Figure 26 Possible database connections required

Figure 27 Typical Site Layout showing database links

January 2008


SeeCarFlow Central application The following is an example of software developed using the information generated from the LPR hardware and software in the field. The SeeCarFlow application uses the data generated by a number of LPR sites the field for various applications. For ETA a similar application would be created and implemented after joint specification.

Overview The central application receives recognition updates from all the sites, analyzes the data and matches the vehicle appearances, calculates the data and stores it to database, and displays it in real time. The application has the following main display options:

• Map – Travel map with real-time statistics • Travel time – travel time between the sites (in tabular form) • Special Vehicle Travel time – travel time for vehicles on ‘allowed’ list • Flow – distribution of the traffic (e.g., 23% of traffic from Site C to A) • Status – diagnostics of all sites

These options are described in the following paragraphs.

Travel Map This option displays a bitmap of the travel map along with travel time figures updated online on the map. The display includes the map bitmap, the location of sites on the map, and the travel time between the points displayed on line segments (in both directions if available). The following figure illustrates an example. Map display example (without zoom) To focus on a specific area the operator can press (with the left button of the mouse) on a specific area, and the program will zoom up at that point showing the vicinity of the zoomed area. Another click will restore the map to its original size.

January 2008


Zoomed area of the map Note: In the example

above, the travel time from Site C to D is 37 minutes, while the travel time in opposite direction (D to C) is 23 minutes. The time is displayed in a purple colour (predefined in the settings) along the line segments (with same color) connecting both sites.

The map display can

also display (upon user selection) the average speed in each traffic segment and the distance between the points.

Travel Time tabular display The following figure shows a typical display of the Travel time tabular display. The Sites are listed as A- H (in this example) and the Site location appears on the right side. The average time between all relevant points is listed in the matrix, where the rows are the ‘from’ site and the columns are the ‘to’ sites. For example, Site C (third row) to Site A (first column) appears as 33 minutes – which was calculated according to the readings from both sites. This value is updated in real-time.

Travel time tabular display of the Central application

January 2008


Special vehicles Travel time The travel time is calculated separately for special vehicles, based on an ‘allowed’ list of vehicles (such as taxis and buses). The user can add, edit, delete and search the list of special vehicles. This list is used then to calculate the travel time for these vehicles. The display is identical to the regular vehicles travel time tabular display. This option displays the traffic distribution: the percentage of the traffic flow from point to point. This data is displayed in a flow matrix, similar to the travel time display. It provides a status of the flow of the traffic from point to point.

Status: LPR unit status When selecting this option the program displays the live status of all LPR units. This includes: • the number of recognition messages received from each point in a given

period, • the percent recognition success (and an alert if a low threshold is reached), • the last time the unit has been initiated or started a recovery process. • On-line Diagnostics results (each unit reports on its status in a periodic cycle) Note that in case of a change in the status of an LPR unit (failure of the on-line diagnostics, or missing messages from that unit), the SeeCarFlow application will display a message and an alarm will be heard.

Settings The number, name and position of the sites are defined in the application settings and could be easily updated if more sites are added. Other parameters can also be changed in the settings. All settings are password protected in order to avoid unauthorized changes.

Travel Time Calculations This section describes the method of travel time calculations as used in the central application.

Travel time Subtracting the recognition times between the sites (see illustration) generates the basic travel time between a pair of sites. Travel Time between Site B & Site A = Time at B – Time at A

January 2008


Figure 4.1: Travel time between Site B & A

Note that not all sites will be considered pairs. A list of legal pairs is defined in the program setting (for all cases that measure the traffic in the correct direction). This calculation will be done separately for standard vehicles and special vehicles (as listed in the ‘white list’).

Average Travel time The average travel time is calculated by averaging the individual travel times that were recorded in a pre-defined period (every several minutes): Average Travel Time = (Sum travel times) / Number of vehicles Since some cars stop on the route or may pass twice, which will affect the calculation. Therefore a standard deviation will be calculated per site pairs. In case a certain time exceeds the standard deviation it will be excluded from the average travel time. The % of permissible change over the standard deviation is an application parameter.

Comparison Accuracy Each vehicle will be matched between the sites, with a comparison accuracy that is defined in the application parameter (‘degrees of freedom in match’). Examples:

1. if the accuracy is 0 then the vehicle code ABC123 must only match ABC123. 2. If the parameter is 1 then ABN123 will match ABC123 (but not ACN123 – the

comparison is performed in the proper position). Furthermore, left or right shift will also be accepted: 1ABC12 will also be acceptable.

January 2008


Even if the match is accepted, the program will first match in full accuracy and only then try the lower degree of accuracy (if defined as such).

Storage and export of Results All calculated travel time statistics will be recorded in a database. This data can be extracted later for off-line processing. The calculated data will also be transmitted over the network for other applications using TCP/IP. Figure 28 Settings in the ASD software The settings above allow the average speed to be determined between site 1 & 2 Figure 29 Example of the results of ASD The image illustrates an example of a speed limit of 100 KM, where the vehicle is exceeding the speed limit by 72 KM.

January 2008


System stability The SeeWay systems are based on proven applications that are running in many installations worldwide - in hundreds of lanes and many diversified applications. The newly developed systems share most of the common modules in these systems (such as the recognition DLL), and are tested in various types of tools and methods that are used by HTS development for years. Thus, their stability is guaranteed by the experience in such systems, the development and test methodologies, and in the proven components that build these systems, Nevertheless, additional mechanisms are used to ensure the stability of the systems. These are part of HTS utilities, which ensure that if the systems will fail, they will be reactivated and also report their failure to external monitor systems. These utilities include: • SeeService – a watchdog utility that periodically checks the aliveness of the application. In case the application does not respond, the application will attempt to rerun the application. If this fails, the utility resets the PC. In any such case the event is written to the Windows event log. • SeeMonitor – this tool resides on a central server, and monitors the state of each system – by checking the Windows event log. It will alert external systems in case of a fatal error. It can also show soft errors (warnings) status, and display a set of graphs of past recognition results, which is a very important diagnostic tool. • SeeCleaner – This utility cleans the old images directories after a specified time has elapsed, and also cleans local diagnostics files. Thus, the system will not grow endlessly in size, a common source of problem in other Windows based systems (which will not happen here). Redundancy In SeeWay systems there is a need to guarantee an absolute up time, i.e the systems always work, even in case of malfunction or required service. The system is designed to work in an automatic redundancy mode, where the 2nd server automatically takes over the functions of the other down server. The dual servers can be set to monitor each other through network messaging and revert to degraded mode if there is a fault in one of the servers. To support this mode, both servers should be connected to the same cameras. In the parameters each lane will be designated as “primary” normal connection, or “secondary” redundancy mode. During the redundancy mode the system is working in a degraded mode, and the performance may be lower than the normal mode in case of certain traffic patterns.

Note that the SeeWay system is limited to 3 concurrent cameras in the redundancy state. So a recommended configuration is to have one server normally connected to 2 lanes, the other server connected to a single lane, while in the backup mode one server will service the 3 lanes.

January 2008


REFERENCE SITES: Record of Similar Projects Completed

The development of LPR started in 1995 and first systems were installed internationally in 1996/7. The first systems were deployed in RSA in 1999 by HTSOL The years experience in ANPR within SA by ASD is over 15 years.

M4 Durban DEMO to Durban Metro • Total number of vehicles detected: 1593 • Distance between Point A and B: 165M

(theoretical distance with D Link directional antenna is 9 KM)

• Full system (Point A & B) hours in operation: 2 • Number of lanes (1 per site), slow lane

Figure 30 Trucks speeding on the M4 towards the airport

January 2008


Figure 31 Visitors to Durban who obey the rules of the road

Figure 32 M4 Durban Demo of ASD

January 2008


PMB to Durban – N3 from Ashburton to Camperdown by I-Cube / ASD Full Name: John Schnell Company: KwaZulu-Natal Department of Transport Business: (033) 3558600 Business Fax: (033) 3558092 E-mail:[email protected] Web Page: http://www.kzntransport.gov.za

Figure 33 Ashburton on the N3 The 3 month demo went from the Ashburton off ramp (Bridge) on the N3 (above), past Camperdown off ramp (below) to Camperdown N3 (Old Road) bridge.

Figure 34 Camperdown on the N3 The distance between the two points was 13.750 KM

January 2008


Ashburton

Camperdown

Figure 35 Average Speed Determination created from 2 sites on the N3

January 2008


January 2008


Above is some data generated from the 1 day test on the N3 over 8 KM. An example for a toll road installation with multiple lanes in Europe is shown in the following photo.

January 2008


REFERENCE SITES:

Record of Projects Completed in SA by I-Cube

Client Nature of works value of work for which the SUB-CONTRACTOR was directly responsible (excluding vat)

year completed

ACSA 3 Lane LPR system for Baggage access control and logging at Oliver Tambo

R180 000.00 2007

SPS Vehicle Monitoring R375 000.00 2006Fourier Systems:

N4 Toll Rd

N3 Toll Rd

LPR Software R67 000.00

R67 000.00

R67 000.00

2007

2006

2005

John Rupert Access Control R175 000.00 2002 SPOORNET HEAD OFFICE

2 Lane LPR system for access control and logging at SPOORNET head office

R220 000.00 2004

AVIS 6 site (multiple lanes per site) LPR for logging vehicles at JHB, DBN

R1,2 million 2002

January 2008


and Cape Town Airport’s and AVIS service areas.

Digital Home Integration Services

Access Control & Logging R75 000.00 2007

HIGHVELD Steel and Vanadium

6 lane Weigh Bridge Monitoring R180 000.00 2006

FANG Access Control R105 000.00 2005 SEE Systems Vehicle Logging R125 000.00 2005

This system is installed in the gates of a South African University. It is used for gate control and theft prevention. The license plate of the cars entering is recorded along with the driver face. This data is compared to the information at the exit and the guard can see that the person at the entrance to the University was different than the person driving the car out. The system also provides statistics and data logging, as well as an on-line surveillance of the gates. After the installation of this system the number of thefts decreased sharply. An actual record of an attempted theft is shown on the right.

The SeeCarTrap system is based on SeeLane recognition system and has special modifications for a roadside mobile system. This system is used for catching cars in cases of warrant of arrest, unpaid fines or taxes and stolen cars. It deals with a database of up to 0.5 million local entries and an unlimited number of remote links. The stand-alone real-time system automatically recognizes the car plate number then searches a database. It sounds an alarm when a car has been detected in the 'black' list, and displays the vehicle and arrest information contained in the record. This revolutionary system simplifies the roadblock operation and thus helps to increase selective enforcement. The system is also connected to a large outdoor display that shows the car number, the car type, the reason for arrest and the name of the driver. This display can be seen by the police officer down the road. All the officer needs to do is wait for the siren, then stop the car and verify the arrest details, as seen in the film clip below.

The system is portable and installed in minutes by the police officer. It is installed in a battery powered lunch-box PC. It operates day and night on a free-flowing traffic at average speeds of 10-80 KMH. The system contains all the elements of a recognition system: hardware (frame grabber, optional IO card, and a special camera/illumination unit optimized for this application) and software (SeeRoad application and a client application). The application includes a special software trigger option which reduces the need to place a detector on the road, making the system portable and easy to install.

January 2008


This system is installed in a traffic police violations processing center in Pretoria, South Africa (in conjunction with Labat Traffic Solutions using the Startrap Intelligence violation data processing system). It is used to automate the process of handling the fine processing (a fast turnaround from film to fine). The application reads both the license plate off the frame - together with violation information. A sample violation is shown in the following photo. The frame, read from the film, includes the view of the car, the vehicle plate, and the violation information - which includes the date, location and speed, and is attached in the upper-right corner. The system performs both access-control, parking and traffic-flow

management functions. It provides solutions for a congested University entrance and enforces an overall traffic policy in its gates and parking lots.

The entrance display provides traffic guidance by displaying one of the 3 options (left 'Guests' for guest parking, middle 'GO' for entrance, and right for 'Inquiries'). The display is controlled by the management software which has multiple authorization lists. Faculty members can use an automated telephone Interactive Voice Response system which accepts requests for temporary passes. The security guards and officers can also change the permit lists on-line. The system keeps records of the traffic events. It also controls the access-control to internal parking lots.

January 2008


The system consists of a cluster of LPR systems, a management software, and an outdoor traffic light display unit. Each of the camera/illumination units (SeeCarHead ) is installed in a anti-vandalism metal cover. The LPR units are based on (SeeLane server application) which interfaces the hardware and performs the recognition process. It sends recognition messages to the client applications. Each of the client applications perform traffic management decisions and connect via network to a management software on a remote server.

This system is installed in the entrance to a new UK office

compound and provides automatic access to authorized cars. The

records of the entry and exit are recorded. The system automatically

opens the gate for vehicles that match the authorized list. A large

outdoor display greets the vehicles (as seen behind the gate).

This system part of a toll road system in South

Africa. The license plate is read and used as a key to fetch the vehicle information from the toll database. The information is compared to a swipe card which is used by the driver. This integrated system reduces fraud and increases the toll income.

The toll system is based on a multi-lane (SeeLane) system which reads and verifies the plate data and sends a message to the toll control application. This

January 2008


application uses the recognition information to obtain the vehicle data, which is matched to the swipe card information. The results are displayed to the operator and also sent to the control room for further processing of the frauds, and long-term data logging.

Vehicle Control & theft prevention

(S.Africa)

Roadblock trapping

system (S.Africa)

Violations Film Processing

(S.Africa)

University Traffic management

(Israel)

Office Access system (UK)

Toll station (S.Africa)

Border Control System (Hungary)

Parking System

(Singapore)

January 2008


Airport Parking (USA)

Bus station control (Colombia)

Average Speed Violation

(Portugal)

C3 Access Control (Israel)

Double Security access Control

(Israel)

University Security Control

(Mexico)

Handheld license plate data entry

(USA)

Parking Management (Korea)

Gated Community (Israel)

University Access (Korea)

Office Security (Israel)

Site Security (Spain)

Gated Community (USA)

Toll station (Colombia)

Shopping Center (Australia)

Casino Valet Parking (USA)

Port Gates (16 lanes) (Ghana)

Gated Community (Israel)

Shopping Center, 36 lanes (Chile)

Airport security, 8 lanes (Israel)

Shopping Center, 16 lanes

(Hungary)

Toll Road, 54 lanes (USA)

January 2008


HTS References Key Global LPR Customers & Installations

Border Crossing • Bartex, Hungary Traffic Management • I-Cube , S. Africa • Engebras, Brasil Security & Law Enforcement • American Science and Engineering – LPR for Container Security • Aquila-Canberra – CCR for Security • Alton High School • IBM – Smart Surveillance System (S3) • SecTec, Mexico Toll Collection • IBI • InTranS (incl. SR125 – San Diego Hwy) • Jupiter Systems (Western Harbor Tunnel, Hong Kong) Parking Services/Access Control • CVPS (Computerized Valet Parking Systems) • DataPark • InterPark/PreFlight • Parking Company of America Airports • Access Control Systems, Honk Kong • Alphawave, Singapore • Intervid, Australia • Consultant Engineering, Australia • Selesta, Spain • DecaLink, Chile Gated Communities • InterAccess Systems • SpectraData Handheld/Mobile LPR • Dierberg’s Markets • ParkTrak Vehicle Services • CommPort - Under Vehicle Imaging Systems (C4) • CruzThru Car Wash • TCS International - Under Vehicle Inspections, Parking Equipment

January 2008


JAI Cameras The cameras for this system will be state-of-the art mega pixel digital cameras that will enable easy remote control via communication cable. Following is a specification of the camera: Model - JAI CV-M4+ or equivalent

Digital 2/3" monochrome progressive scan CCD camera 1392 (h) x 1040 (v) 6.45 µm square pixels Extended IR sensitivity 10 bit video output as Camera Link LVDS version with 8 bit video output Full 1380 (h) x 1030 (v) frame readout in 1/24 second Higher frame rates with partial scanning or binning Partial scan to 1/8 and vertical binning Edge pre-select (EPS) and pulse width control (PWC) trigger modes Restart continuous trigger (RCT) mode Analog video output for controlling auto – iris lenses Shutter speeds from 1/24 to 1/10,000 second in 10 steps Trigger and timing signals as LVDS or via Camera Link Setup by switches or serial control (short ASCII commands) Windows 98/NT/2000/XP setup software

1).Camera+Lens Dimensions:

S6X11 2/3" 11.5~69mm Manual Iris, C-mount

Compatible with 2/3", 1/2" & 1/3" CamerasFocal Length: 11.5~69mmMaximum Relative Aperture: 1:1.4Iris: F1.4~CloseZoom Ratio: 6XMount: C-mountMinimum Object Distance: 1.0m (from front vertex) Angular Field of View: 2/3": 41.9° x 32.0° at 11.5mm

7.3° x 5.5° at 69mm1/2": 31.1° x 23.6° at 11.5mm

5.3° x 4.0° at 69mm1/3": 23.6° x 17.8° at 11.5mm

4.0° x 3.0° at 69mm1/4": 17.8° x 13.4° at 11.5

3.0° x 2.2° at 69mmOptical Back Focal Distance: 17.93mm (in air) Operation: Zoom: Manual

Focus: ManualIris: Manual

Operation Temp: -10 ~ +50°C (+14 ~ 122°F)

January 2008


Filter Size: 46mm P0.75Weight: Approx. 395g (13.9oz)

Camera Dimensions: Camera +Lens Dim: L=189mm W=88mm H=67mm

January 2008


Pleora Card Dim” L=89mm W=21mm H=62mm

The Card is located near by the camera as shown in the next picture Connected with Camera link cable from camera to Pleora Card

Total Dimensions: From Heater to Terminal Block: L=350mm W=120mm H=110mm

January 2008


2). Enclosure: L= 450mm W=135 H=140mm

January 2008


January 2008


JAI Camera Pins Description The following diagram defines pins connectivity description of JAI camera

Figure 36 Pin layout The following tables show the characteristics of the images captured on the SeeWay system. Figure 37 Image Characterises from the JAI camera used in SeeWay

January 2008


IPort PT1000-CL IP Engine The IP engine interfaces the JAI cameras and transfers the images and control over the Gigabit link. Its main features: Model : Pleora PT1000-CL or equivalent High-performance, ultra-efficient connectivity between camera link cameras and Gigabit Ethernet Links or LANs acquires images from a wide range of cameras, including JAI delivers long-distance bi-directional links over inexpensive CAT-5 copper LAN cable

serial RS232 control over camera free-running or externally triggered – flexible acquisition modes Inputs : 2 TTL inputs, 1 LVDS, 1 optically isolated input Outputs : 2 TTL outputs, 1 optically isolated output Power supply: 4.5V – 16V @ 4.5 Watt CE certified and FCC

Figure 38 IP engine interfaces JAI cameras, transfers images over Gigabit link. SEEWAY Camera JAI: CONNECTIVITY REQUIREMENTS: Data rate is 44 times p /sec x 1300 x 512 bytes = 30MB = 0.25G =-==> 4 cameras per site. 3 sites = 0.75G/s

January 2008


Theory of operation The operation of the system is as follows: When the vehicle detector (laser) signals the end-of vehicle (low going signal), it will trigger the application (via the IO card) telling it to take a series of pictures. The SeeWay application will capture the images from two cameras that are installed on that lane – both front and rear. The application also controls the IR illumination level via the IO card – switching from off (the normal idle state) through low, medium and high illumination states. This set is predefined in the application’s parameter settings, and could be defined for different time of day (such as night and day capture sets). This is for the front camera only, due to the headlights. SeeWay will also capture an additional image using an additional colour camera that will be positioned to cover the entire width of the lane. This camera will supply a view of the lane which can be used for a manual review – it can be used to verify the colour of the vehicle’s body.

Single Lane LPR system The application analyses each of the captured images and extracts the plate string from each image. After collecting and comparing the results from all captures, the application determines the final result and selects the best image. It then outputs its 2 constituents: the JPEG image and OCR Hardware Components description SeeWay components are shown in the following diagram. The system is composed of a number of cameras; all connected to the frame grabber (video input) and to the I/O card (illumination control). The I/O card also receives dry-contact inputs from the loop detectors, and could also open a gate. The Windows application (SeeWay) runs in the PC and controls the system. It sends the recognition results by a DDE message, and to the network to a remote application or database.

January 2008


Pulsed Illumination unit The highlights of the unit is:

• B&W camera with mounted lens • Pulsed LED array (Near Infra-Red spectrum) • Case (IP 65 , weatherproof, Enforced Poly-Carbonate, UV protected) • Control circuit (sync and pulse control, illumination level control) • Power supply (3A 15VDC) and cables • Mechanical interface (with 2 degrees freedom) • Inputs: 2 lines TTL (3 levels of intensity + off) • Output: Composite Video 1Vp-p / 75Ω • ISO 9002 Manufactured (by Hi-Tech Solution’s sister Company)

The unit is integrated in the LPR unit Windows application, which switches the unit on (only when the vehicle is present), controls its illumination level in various sequences (based on the recognition results and the setting parameters), and captures its images for recognition and optional archiving.

This compact and highly integrated unit is installed Worldwide in hundreds of lanes in various applications and configurations.

The above image illustrates the use of the IR.

January 2008


The above image illustrates the pulsed operation of the LPR system Light Safety Notations Note on Compliance with International Standards: The illumination unit complies with International Standard IEC 60825-1, for Class 1 LED (light emitting diodes) product containing Class 1 LED’s. Class 1 LED product poses no hazard to the user or to any other person present near the illumination unit. The use with the illumination unit is totally safe and needs no specific precautions.

Figure 39 Pulsed IR illumination

Figure 40 Wiring for the Illumination Units

January 2008


January 2008


I/O Card The PCI-1751 is a 48-bit digital I/O card based on a PCI bus. Its 48 bits are divided into six 8-bit I/O ports and users can configure each port as input or output via software. The PCI- 1751 also provides one event counter and two 16-bit timers, which can be cascaded to become a 32-bit timer. 48-bit Digital Input/Output Card for PCI Bus Main Features

Emulates mode 0 of 8255 PPI Buffered circuits for higher driving capacity than 8255 Output status read-back Interrupt handling 48 TTL digital I/O lines

January 2008


Terminal Block (TBL): The terminal block is connected to the I/O card with a flat cable, and has a block of screws and LEDs that enable an easy connection to the inputs (the trigger) and outputs (the illumination control). The terminal block has a plastic cover that hides and protects the terminal block (it is not shown).

See Way Connection table

January 2008


See Way Schematic Diagram The following diagram defines the main components and the technology connectivity.

The following diagram defines the details connectivity between the main components of See Way system.

January 2008


Camera Settings Each camera will have a field of view of about 2.8M (horizontally) by 2.1M (vertically). The image size in full resolution is 1380 X 1024 pixels, which will yield plate sizes of 150 X 60 pixels at full resolution. Each camera is utilizing a single interlaced frame of 1380 X 512 pixels. The JAI cameras have different capture modes and the system will enable different settings of the cameras in order to optimize the recognition versus the throughput. The shutter speed is also adjustable, and the system can handle the speed requirements (200 KM/H) at 1/2000. Video flow After the cameras have acquired the images data, they will be transferred to a corresponding iPort video to IP unit. Each iPort unit corresponds one-to-one with each camera. The iPort units convert the camera-link interface to data that will be transmitted on the VES Gigabit, a closed Gigabit LAN (separate from the NCS) whose sole function is to transfer image data from the cameras to the VES servers, and to send and receive commands to/from the lane controller. All cameras are connected via a Gigabit switch (8 ports), so the VES server can actually interface with each of the iPort units to all the lane cameras. This is useful in case one of the VES servers is down, and the other VES server can be commanded to handle the other camera as well. When the VES Server receives the image data, it will convert the data to arrays of images. It then proceeds to perform image enhancement and recognition. It will select the best result out of the captured images. Transaction number The VES Server and the Master Lane Controller (LC32 Lane Controller) shall synchronize each picture with a transaction. To do this, the lane controller will feed the SYSTEM TIME and the TRANSACTION SEQUENCE NUMBER to the VES Server (the machine doing the OCR) at the precise moment it triggers the camera, over the solid state relay, to take a picture. The communications will take place over a UDP connection to the VES Server. The VES Server client application will hold this information, and when the OCR is finished for a particular snapshot, will apply a FIFO rule for each request. The message shall have the following format: STX-BB-HHMMSS-BBBBBBBBB-ETX Where: STX BB = Lane ID HHMMSS = System Time BBBBBBBBB = Transaction Sequence Number ETX

January 2008


ASD KEY COMPANY PERSONAL PROFILE

With over 78 sites in South Africa, the I-Cube LPR system is the leading software solution. I-Cube was the first company in Africa to implement real time (sub second), high speed (over 263 KM /H), multi-lane LPR solution in a free flow environment, incorporating average speed determination (on an average 35 000 vehicles a day).

Barry Fryer Dudley, the CEO of ASD is a committee member of the Computer Society of South Africa. Presentations: Neural networks to enhance safety in local authorities: automatic identification, tracking and alarm at TECHNOLOGY IN LOCAL GOVERNMENT RAISING LEVELS OF SERVICES DELIVERY THROUGH TECHNOLOGY 20-21 JUNE 2006 – MIDRAND Education: MBA at the University of Natal, speciality: IT Information Management & E-Commerce. The MBA dissertation, Casino Exclusion Technique Exploration - Framework Development, examines the possible solutions to excluding problem gamblers from SA casinos. University of Natal, Pietermaritzburg, Republic of South Africa – M.S. thesis (Cum Laude) in Microbiology (April 1999). Thesis Title: “Application of Image Analysis in Microecophysiology Research: Methodology Development.” Publications: The Industry Journal for Security and Business Professionals Volume 11 No. 2 Pg 34/35 DIVERSITY OF LICENSE PLATE RECOGNITION APRIL SECURITY FOCUS (Vol 22, No. 4) Facts, features and benefits of facial recognition

A. Refereed Journals Invited and Published B.T. Dudley, C.A. du Plessis and E. Senior. “Managing leachate in landfills through manipulation of soil cappings: Image analysis studies”, Binary - Computers in Microbiology, Vol 6, 120-127. (1994) Submitted and Published B.T. Dudley, A.R. Howgrave-Graham, A.G. Bruton and F.M. Wallis. “The application of digital image analysis to quantifying and measuring

January 2008


UASB digester granules”, Biotechnology & Bioengineering. 42, 279 - 283. (1993)

B. T. Dudley, A. R. Howgrave-Graham, H. Isherwood and E. Senior. “Laboratory-scale UASB digesters (with/without conditioning tank and recycle):

efficacy to treat increased hydraulic loads”, Water SA. 19, 313 - 318. (1993)

B. Papers Presented at Professional Meetings Invited and Published B.T. Dudley, C.A. du Plessis and E. Senior. “Managing leachate in landfills through manipulation of soil cappings: Image analysis studies. Image Analysis of Microbes in Their Habitats”. Society for General Microbiology Meeting on Image Analysis at Warwick, United Kingdom, 5 - 7 January 1994. Submitted and Published B. T. Dudley, E. Senior, A. G. Bruton and F. M. Wallis. “Image analysis methodology development for use in microecophysiology studies of microbial associations in landfill cover soil”. Seventh International Symposium on Anaerobic Digestion, Cape Town, 23 - 27 January. (1994)

January 2008


CURRICULUM VITAE : Dr. M. F. MITCHELL,

CHAIRMAN OF ASD

1. Personal Details

Name Dr Malcolm F, MITCHELL Nationality South African Profession Civil Engineering: Registered Professional Engineer. Specialisation Transportation Engineering and Administration. Date of Birth 26.11.1935 Company Consultant in single person Private Practice, following

retirement from Department of Transport.

2. Key Professional Experience

Dr Malcolm Mitchell had a distinguished career in civil engineering and public administration spanning over 40 years before he retired as Deputy Director-General at the South African National Department of Transport in 1998. His Doctoral dissertation in Transportation Engineering related to a strategy for developing a road network in Southern Africa and extensively dealt with institutional and financing aspects of road administration, including road charging/pricing and fund allocation procedures. His thesis for the Master’s Degree in Public Administration related to the development and management of a toll road system for South Africa. He has had over 70 papers published, received the SAICE Transport Division Award for outstanding services to the Transportation Engineering Profession (1994) and served on both the S A Roads Board and the Board of Control of the S A Rail Commuter Corporation. He was the first Chairman of the South African Committee of Land Transport Authorities, and the “Roads Function” Committee, a Treasury body responsible for managing the allocation of all roads funds in South Africa, as well as many other government and professional committees. He was also an external examiner at several universities, the President of the Chartered Institute of Transport in Southern Africa and a Senior Fellow and Council Member of the South African Institution of Civil Engineers. Key areas of experience include: • Road Management and Toll Roads • Quality Control of Road Construction • Transport Policy Formulation and Implementation • Civil Engineering Contract Documentation and Dispute Adjudication

January 2008


• Road Design and Supervision of Road Construction and Contracts • Geotechnical and Pavement Engineering • Road Financing, Project Programming and Strategic Planning for Transport • Urban Transport Planning and Management

3. Education and Qualifications

• B.Sc.Eng. (Civil): University of Natal, 1956; Won Certificates of Merit for various individual courses; Awarded status of “Scholar of University of Natal” Won final year civil engineering design thesis prize

• B.Admin (Hons): University of South Africa, 1986.

• M.Admin (Public Admin): University of South Africa, 1989; Distinction level passes in Advanced

Public Financial Management and Advanced Public Policy Making. Dissertation : Administration of Toll Roads in South Africa with Special Reference to Policy Making, Organisation, Financing and Control

• D.Eng (Transportation): University of Pretoria, 1991; Dissertation : Contributions

to Establishing an Appropriate Road System for Southern Africa

4. Some Professional Affiliations, during career.

1.1_ Previously: - • President, Chartered Institute of Transport in South Africa • Member (and often acting Chairman) South African Roads Board • South African representative on World Road Association (PIARC)

Permanent International Commission • Member of the Executive Committee of World Road Association • Chairman South African Civil Engineering Advisory Council • Member of Council, and Executive Committee Member, South African

Institution of Civil Engineers • Member of Civil Engineering Joint Consultative Committee (JCC)

comprising SAICE, SAFCEC and SAACE representatives • South African Representative on SATCC Committees • Chairman South African National Committee on Tunnelling • Member of Board of Directors of South African Rail Commuter

Corporation • Chairman : Committee of Land Transport Officials and Committee of

State Road Authorities • Deputy Chairman, National Road Safety Council • Chairman : Annual Transportation Convention Organising Committee • Chairman : Transportation Division, South African Institution of Civil

Engineers • Member : CSIR Transportation Division, Research Steering

January 2008


Committees • Member : Various Metropolitan Transport Advisory Boards • Currently Member : Engineering Council for South Africa, Professional

Advisory Committee for Civil Engineering

5. Experience Record

1998 to date Following retirement from Department of Transport, established a one person professional consulting practice, specialising in Transportation matters. Was Specialist Consultant to Transportek Division of the Council for Scientific and Industrial Research until the end of 2005, Chairman of the Dispute Adjudication Board for the Maguga Dam project in Swaziland, and has carried out work for the Development Bank of Southern Africa and some consulting engineering firms. He is currently Executive Director of the South African Road Federation and a member of the Civil Engineering committee of the Engineering Council of South Africa. He is currently registered with the Johannesburg University as a D.Phil. student, with a dissertation examining the development and impact of transport policy in South Africa during the 20th century.

1989 to 1998 Department of Transport - Deputy Director-General

Overall responsibility for central government activities in respect of all aspects of Land Transport in South Africa, including roads, urban transport, road traffic management and safety, transport policy formulation and strategic planning, research and development and freight and public passenger transport.

1984 - 1989 Department of Transport (Chief Director of National Roads) Responsible for overall management of all National Roads in South Africa

1980 – 1984 Department of Transport (Chief Engineer/Director) Overall responsibility at central government level for National Road financial management and project programming and strategic planning, as well as urban transport planning activities for all national roads and metropolitan transport areas in South Africa.

1972 – 1980 Department of Transport (Assistant Chief Engineer) Head of Materials and Pavement Design Section and, responsible at central government level for supervision of road design, construction, quality control, geotechnical design, and pavement maintenance activities on all National Roads (including research).

1970-1972 Department of Transport (Assistant Chief Engineer) National road design and supervision of construction and maintenance contracts at regional level. Route location for new national road (N3) over the Drakensberg mountain range (100-km)

1966 – 1970 Consulting Engineer (Senior Engineer to Associate Partner) National and provincial road design (Geometric and pavement), • Supervision of road contracts • Geotechnical engineering design and management of geotechnical and

materials laboratory testing

1962 – 1966 Natal Roads Department (Engineer Grade I to Principal Engineer)

January 2008


Quality control of road construction, geometric, pavement and geotechnical design of provincial and national roads, bridges and interchanges (200 km road and 5 interchanges) and management of materials testing laboratory.

1956 – 1962 South African Railways and Harbours On site responsibility for construction of railway tunnels (five twin tunnels, including the current second longest railway tunnel in South Africa), approximately 50 km of new railway lines involving heavy earthworks various new stations and bridges and major mechanical workshops, as well as maintenance of 250 km of open line. ________________________________________________________ 6. Selected Career Achievements ____________________________________________________________________

• Initiated, promoted and directed introduction of toll roads in South Africa as a road pricing financing mechanism.

• Initiated and administered the first two comprehensive National Transport Policy Studies between 1984 and 1996.

• Initiated, promoted and participated in research and development of procedures for road financing, fund allocation, project prioritisation, road needs studies and cost/benefit analysis for roads, in South Africa.

• Initiated, promoted and directed the extensive use of concrete pavements for heavy-duty roads in South Africa as well as drawing up of a design manual for concrete roads.

• Promoted the use of, and procedures for, statistical quality control for road construction.

• Introduced and promoted the first rational; planning approach to the provision of passenger transport services in Regional Service Council and Metropolitan areas in South Africa.

• Promoted the early development (circa 1973 – 1980) of road pavement management systems in South Africa.

• Initiated, promoted and directed developments in respect of revised approaches for road management in South Africa, i.e. the Road Agency concept.

• Involved in initial formulation and development of a project to draw up a Strategic Plan for Transport in South Africa.

• Promoted and directed initiation of Centres of Development in Transportation at selected South African Universities as well as Technology Transfer Centres for Transportation.

• Initiated and promoted first “Build, Operate and Transfer (BOT) National Road Project in South Africa (N1) in 1993.

• Recipient of CSIR award for “Contributions to Transportation Research”. • Recipient of SAICE award for “Outstanding Contribution to the Transportation

Engineering Profession.”

7. Publications

Has had over 70 refereed papers published, locally and overseas, primarily in the fields of Transport Policy and Institutional Arrangements, Road Management, Road Design and Road Financing, including Toll Roads and Road Concessions. Has won “Best Paper” awards at Conferences and in the SAICE Journal, as well as presenting papers, by invitation, at the World Bank.

January 2008


SEEWAY SOFTWARE This section details the software elements of the SeeWay system.

The Image processing DLL The SeeWay system calls SeeCar image processing DLL that analyses the captured images of the vehicle. The DLL is described in a separate document (see APPENDIX). It is usually configured to the specific country using a configuration file (format.ini). Main Display The main window is designed to display as much information as possible in a friendly user interface (the user does not need to switch between any child windows during normal operation). The window is divided into several display panes, where each pane is responsible for a single system task. The different panes are described below: - Image Display - shows video from the camera (from one of the lanes) - History Log - displays list of identified vehicles (index, code, lane, time, image path) - Status Window - system messages An example of such display is shown in the following figure:

January 2008


The vehicle that is shown was captured with a front camera and is displayed on the image display. Its license plate number and the date/time are shown in the left/bottom scrollable history list. Its license number is shown in the top-left corner. The system status (triggers and messages) is shown in the right list. SETTINGS Parameters settings The application is configured using a set of parameters that can be controlled using the SeeWay options. There are different settings windows: • Lane definition (see example below) • Camera definition • View definition • General parameters • Save images parameters (see example in the next page) • Communication parameters • Diagnostics A sample window is shown below and in the next page. For all windows and an explanation of each option – refer to the installation manual, or use the HELP button.

January 2008


Images files One of the main purposes and advantages of image based recognition systems is the creation of the image files. Due to the high resolution, the images are kept in a jpg format, with a quality level that is defined in the settings. The user may select one of the 5 levels (lowest quality to highest quality), or save in bitmaps. The other parameters include the local images directories path, and the option to save the images in a daily sub-folder (as in the example below), weekly or single directory. The naming of the images files is composed of an optional camera prefix and a random number that is assigned to the image. Thus, all images are identified in a unique identification for each lane. This unique number may be used for creating a transaction number.

Figure 41 Setting Page

January 2008


CABINET DOOR SIGNALLING DEVICE I-Cube uses the BANDIT Activ device to ensure the remote housings are not tampered with. This will alarm if:

- The door is opened without authorisation; - The remote housing tilts or moved in any way; - If the system is stolen, it can be recovered; - The power goes off; - Other signals as required.

Our most-affordable 'entry level' system , Active Tracking hallmark is the key to our enviable Recovery Rate and renowned level of Client Satisfaction. Peace-of-Mind Positioning delivered within seconds of Client Request.

BANDIT Probable-Theft-In-Progress Alerts

• Power or Battery Disconnect - often indicates a crime in progress • Automatic Backup Battery Activation • Alerts accompanied by Vehicle Positioning • Activation of Beacon Transmitter for final pinpointing of 'distress signals'

BANDIT Tracking Unit Self-Test

• Automatic Testing - no added responsibility for ETA • Results regularly transmitted to BANDIT 24-Hour Control

BANDIT Bonus Benefits

• Private Recovery Teams with Helicopter Support in all major centres • Stolen items returned as found - guaranteed • MTN network: of 5 000 towers covering one million square kilometres - 'Everywhere

You Go'

BANDIT is networked into the GSM grid of cellular giant MTN - 5 000 towers covering one million square kilometres of South African terrain. Access to the dedicated SMS Server means the added advantage of Priority Messaging. Not only does GSM constitute the undisputed medium of the future, but in terms of Tracking it furthermore meets all demands of the country's stringent Insurance Underwriters. COST: 24 month contract @ R129/M (Cash price of R1 690) or 3 year contract at R179.00

January 2008


Noptel CM3 sensors in traffic control Background Noptel developed in the late 90' the CM sensor family for industrial and traffic control measurements. During the last years we have delivered these sensors for traffic control in Finland, Spain, Germany, Austria, Hungary, Netherlands, UK, Brazil, South Korea, Australia, Argentina, USA, South Africa and China, for example. Totally more than 2000 units are in use. About half of these are in speed measurement task, the other half in vehicle tracking, classification, detection and red light control task. Most sensors have been connected to a camera system, working with LPR.

The sensors are meant for fixed installations, outdoor use and to work often with other sensory or control devices, like cameras. Some of the typical applications are: - accurate triggering of a camera for license plate recognition, from either the front side or the rear side of the vehicle - vehicle speed measurement using one unit, triggering the LPR camera in speed violation case, either from the front side or the rear side of the vehicle - vehicle speed measurement using two units, triggering the LPR camera in speed violation case, possible to combine with vehicle classification data - vehicle average speed measurement between two sites (section control) - vehicle axel counting, multiple lane, speed measurement

January 2008


- vehicle classification, height and length measurement - vehicle recognition for traffic light control - speed sensor for portable speed camera - over height control for tunnel entrance These devices represent a perfect choice for intelligent traffic camera triggering, vehicle classification or speed measurement. The units are small in size, light in weight and economical in power consumption, and are suitable for outdoor use in harsh environments. Similar installations can be used for measuring the speed of approaching or departing vehicles (10 to 250km/h). Operation One typical application for a laser sensor is vehicle detection, when the vehicle is approaching an LPR camera or driving away from it. The principle of operation is to measure the distance from the object quickly and to use this to define the exact triggering moment. A typical sensor installation is five to seven metres above the ground, looking forward and down at the road. When the vehicle enters the trigger area defined by the parameters, the sensor sends a pulse to the camera. The triggering accuracy in such cases can be as high as 5–10 cm (or one millisecond), depending on the installation.

January 2008


TD136 SINGLE CHANNEL DETECTORS

The innovative TD136 series of single channel inductive loop vehicle detectors used to detect vehicles presence by means of an inductive loop buried under the road and have all the features and benefits found on much larger modules. No longer is it necessary to make compromises when selecting a detector for Traffic control, counting or traffic analysis - these "one-chip" microprocessor-based units are suitable for them all. Available in standard & custom variations these detectors can cater to your every system requirement.

APPLICATIONS · Traffic Control Applications · Vehicle Counting · Toll Systems · Traffic Analysis

FEATURES

· Compact Size:

This compact and well engineered housing combines all of the industry requirements regarding features and functionality and allows this detector to be incorporated into any new or existing traffic detection system.

· Diagnostic Capabilities: Comprehensive diagnostics capabilities allow for accurate diagnosis of loop and installation problems.

· Selectable Presence: The output of the presence relay can be selected to maintain an output for an extension period, or defined presence output times.

· Loop Isolation Protection: The loop is isolated and provides protection against lightning and transient damage and allows for operation with single point to ground sensor loops. Added filtering reduces interference from external noise.

· Loop Frequency Indication: Interference between adjacent loop / detectors can be determined by an integral indication, and eliminated by changing the frequency settings.

· Environmental Analyser: Continuous monitoring of external parameters ensure reliable product performance & operations under all environmental and power supply conditions.

· Delay on Detect: Provides a turn-on delay, thus allowing selective detection which is often useful for screening out unwanted inputs.

· Visual Fault Monitor: A fault indication is provided in the event of the loop input becoming faulty, or alternatively if the loop is out of the operational range. This feature will help in localising the fault in the event of a maintenance call-out.

January 2008


Self-tuning Range: 20 – 1500 µH Sensitivity: Four step adjustable on faceplate

High 0.02% L/L Med-High 0.05% L/L Med-Low 0.1% L/L Low 0.5% L/L

Frequency: Four step adjustable on faceplate 12-80kHz (Frequency determined by loop geometry)

Output Configuration: 2 output relays: Relay 1 = Presence output (fail safe) Relay 2 = Fault output (Fail-Safe)

Pulse Output Duration: Approx. 150 ms (factory option – 250 ms). Presence Time: Limited presence - 1 hour for 3% L/L or permanent

presence option Operating Modes: Four-way mode selector on faceplate:

Limited presence / 1 sec, 4mm, 40min Delay Output (0,10,20,30 seconds)

Indications: The following faceplate indications are provided: Red LED - Diagnostic Green LED - Channel indicator Tuning - on steady followed by flashed frequency count (x10kHz) Undetected - off Detect - on steady Fault - on with short off periods

Protection: Loop isolation transformer, zener diode clamping on loop inputs and gas discharge tube protection.

Power Requirements: 120 V AC 15% 48 - 60Hz 230V AC 15% 48 - 60Hz 12-24V AC/DC Requirements - 1.5VA max @ 230V

Output Relays: (Rating and Type)

Presence Relay - 5A @ 230V AC Change-over contact (Fail-Safe) Fault Relay - 5A @ 230V AC Change-over contact

Operating Temp Range: -20°C to +70°C (Circuit sealed against condensation) Material: High heat ABS blend Dimensions: 76mm (high) 40mm (wide) x 78mm (deep) Mounting Position: Shelf or DIN-rail socket Connector: Single rear mount 11-pin ubmangnal (86CP11)

Option - 1 metre flying lead TD 136 TYPICAL WIRING CONFIGURATION FOR STANDARD MODELS.

January 2008


Training of 4 Staff For

ETHEKWINI MUNICIPALITY

Document Control Document Information

Information Name Description Document ID 100/IC/001-07 Document Owner I-CubeIssue Date 2007-10-08 Last Saved Date 2007-10-08Document name Project Management for Computer Training for I-Cube obo E. T. A. Document History

Information Version Issue Date Changes

1.0.0 2007-10-08 Nil Document Approvals

Information Role Name Signature Date Project Sponsor ETA 2007-10-08 Project Review Group 2007-10-08 Project Manager TBA 2007-10-08 Procurement Manager TBA 2007-10-08 Communications Manager TBA 2007-10-08 Project Office Manager Barry T. Fryer Dudley 2007-10-08

January 2008


Table of Contents

1. Executive Summary

2. Business Problem

Root Cause Analysis

Problem Analysis

3. Alternative Solutions

3.1 Option 1

3.1.1 Description

3.1.2 Benefits

3.1.3 Costs

3.1.4 Risks

3.1.5 Assumptions

4. Recommended Solution

5. Implementation Approach

Project Initiation

Project Planning

Project Approach

Project Execution

Project Closure

Project Management

6. Appendix

Supporting Documentation

1. Executive Summary

The ETA is currently building Public Transport Lanes along the Western Freeway in Durban. These lanes are being constructed with the sole aim being the use of the public transport system in Durban.

2. Business Problem

In conjunction with Private enterprise, the ETA requires these Public Transport Lanes to be monitored on an ongoing basis. This will require the training of 4 staff, to be trained in the systems and maintenance thereof.

January 2008


2.1 Root Cause Analysis Training is to be provided to 4 staff of ETA.

2.2 Problem Analysis Business Problem This is a new venture for the ETA as no similar system exists and initial set-up and training will be required. Business Opportunity As there is only 28 days in which to conduct the said training before going live, including installation and set-up, time is critical and all resources need to be focused.

3. Solution 3.1 Option 1

3.1.1 Description The staff will be trained on the necessary systems in the basic set-up and operation of the said operating systems.

3.1.2 Benefits The staff gets to undertake and view the installation of the basic systems set-up.

3.1.3 Costs The cost of training the 4 staff members individually is detailed in Schedule B.

3.1.4 Risks The possibility of there being insufficient time is a real possibility and can not be understated.

3.1.5 Assumptions It is assumed that the 4 staff members would have an advanced level of training; i.e. at least M+4, with an advanced level of computer knowledge. If this is not the case, additional levels of training will be required.

3. Recommended Solution Training Solution

Training in the said solution is done by I-Cube on site and in the ETA control room.

January 2008


Proposed Training course outline As the current skill and knowledge level of the delegates is unknown, it is proposed that the training is designed in modules that can be added to, changed or removed from the training programme.

Module 1: PC orientation and Microsoft Windows skill builder Contents: The first half of this module would focus on familiarising the delegates to computers and the terminology. The second half of this module would focus on introducing the delegates to Microsoft Windows and particular terminology in the graphic environment. Specific features would include managing windows, working with multiple windows, copying or moving data between different windows and managing files at a very basic level. Length: one day

Module 2: SeeWay software Contents: This module would focus on the theory and practical aspects of the SeeWay software which is used for monitoring average car speed. The delegates would learn how to use the optical and hardware systems necessary for this software. Depending on the nature of this system, this learning may take place in the training venue, in the field and in the Control Room. Length: one day

Module 3: SeeCarSpeed software Contents: The focus of this module would be on the theory and practical aspects of the SeeCarSpeed software which forms the front-end of this system. Depending on the nature of this system, this learning may take place in the training venue, in the field and in the Control Room. Length: one or two days depending on the technical requirements Assessment: A post-training assessment will be conducted to determine whether there has been a transfer of knowledge and skills. This assessment can be done immediately at the end of the training programme or, alternately, after a few days which would allow the delegate to experiment and practice with the system. The decision on when to assess would ultimately be driven by the urgency of getting the delegates to use the system confidently. The assessment would be of a practical nature with the delegates needing to demonstrate that learning had taken place and that they would be able to competently utilise the system to create an outcome.

On-site Requirements: ! A training venue with a minimum of 5 computers: 1 each for the 4 delegates

and 1 for the trainer.

! A data projector connected to the trainer’s computer.

January 2008


! Windows XP to be installed on all the computers.

! The SeeWay and SeeCarSpeed software would need to be installed on all computers, alternately training on this software would need to be done in the Control Room.

Times: Note: Training times are 08h30 until 16h00 with a 45 minute break at 13h00

Negotiability: As there are currently many unknown factors regarding the training of these delegates, it is important to note that the above schedule of training is a proposal only and that any of the modules and time frames are open to negotiation to suit the needs of the client. 5. Implementation Approach

5.1 Project Initiation

The project is to be initiated at the announcement of the tender and once all data to be trained has been identified. 5.2 Project Planning

The Project planning team will embark on the training schedule once the ender announcement has been awarded.

5.3 Project Approach The project will be approached from a basis that staff members have limited or no knowledge at all.

5.4 Project Execution An attempt will be made to have the required training completed before completion of the said tender, 29 days from issue. Thereafter 1 day per month.

5.5 Project Management The project will be managed very closely by the Principal Contractor, I-CUBE IMAGING.

6. Appendix Any and all supporting documentation listed in the APPENDIX will be provided.

January 2008


SUPPORT & MAINTENANCE Client: Group 5 / ETA Project Name: Maintenance of Automatic Number Plate Recognition (ANPR) Equipment Project Summary: Public transport lanes require enforcement to prevent abuse. I-Cube provides its LPR technology and maintenance services to assist Group 5 to provide maximum uptime for the solution. Project Background: Enforcement forms a critical link in the provision of public transport lanes. Any downtime or maintenance activities can interrupt the services on the road and reduce overall enforcement effectiveness. Although the objective seems to minimize maintenance, safety and long term availability of the assets are critical and require an optimized maintenance plan. The maintenance planning should therefore take account of the asset condition, utilization and historic maintenance activities. Group 5 has outsourced the maintenance of the LPR solution asset to a third party contractor. It is therefore critical to understand the exact maintenance requirements and control the execution thereof. Project Objectives: The objective of the project was to provide Group 5 with the means to obtain maximum uptime and optimise maintenance plans. The primary requirement was to reduce maintenance cost and improve overall asset condition. FACTORY WARRANTY AND MAINTENANCE PLAN The Factory Warranty and Maintenance Plan shall remain valid for the period specified in the written Quotation or Sales Proposal commencing on the date of delivery subject to the following terms and conditions: The Factory Warranty will include: All transport and insurance whilst in transit to and from dealer/manufacturer repair facilities for any fault arising within 365 days after delivery, install and operation. All parts except those damaged by:

- Lightning - Use of incorrect electricity supply - Excessive dust.

January 2008


The Factory Warranty will exclude: All transport and insurance whilst in transit to and from dealer/manufacturer repair facilities for any fault arising more than 365 days after delivery. All labour. Customs duties, taxes and clearing agent fees in respect of items imported into South Africa. The Maintenance Plan will include: All software/firmware updates and upgrades. Repairs to media All transport and insurance whilst in transit to and from dealer/manufacturer repair facilities. All parts, including copy-protection hardware, except where damaged by:

- Lightning - Use of incorrect electricity supply - Excessive dust.

The Maintenance Plan will exclude: Customs duties, taxes and clearing agent fees in respect of items imported into South Africa. All services in respect of software including but not limited to installation, configuration and training Manuals which are not supplied by the original manufacturer/publisher Software crossovers or trade-ups to enhanced or more advanced variations of the original package Optional add-on modules or enhancements which are sold separately to regular upgrades by the manufacturer/publisher The Factory Warranty and Maintenance Plan will be void in event of: - Unauthorised attempts to repair, alter, modify or reverse engineer the function of any part or assembly or any software component or module - Any contravention of the software license and copyright conditions of the manufacturer/publisher. - Missing Warranty Seals or where such seals have been tampered with. - Accidental damage. The following steps will be taken in the event of not being able to solve a problem by telephone, by fax or by email in respect of a product covered by the Maintenance Plan:

January 2008


Will send a technician to attempt an on-site repair or will alternatively send a driver or courier service to fetch the product. All boxes and related packaging material remains the property of Neville Clarence Technologies (Pty) Ltd. and should be retained and stored by the client for the duration of the Factory Warranty or Maintenance Plan. In the event of it being necessary to return a product which is covered by the Factory Warranty or Maintenance Plan the client is to pack the product in the original box, using the original packaging material, ensuring that the carton is well sealed. The Client is to contact I-CUBE for packaging instructions in the event of the original packaging having become mislaid or damaged. The Client is to ensure that the package is clearly and accurately addressed and is to call I-Cube when it is ready for collection. I-Cube assumes no liability for the loss of miscellaneous items including but not limited to power, video signal and interface cables, AC adapters/chargers, speakers, battery packs, headphones or headsets, carrying bags, software or manuals, which accompany products returned for repair unless the client has been specifically requested to return such items. In the event of I-Cube declaring a hardware product which is covered in terms of a Factory Warranty or Maintenance Plan unrepairable or uneconomical to repair, then I-Cube shall reserve the right to either:

- Replace it with a new, functionally-comparable product of similar value or;

- Replace it with a functionally-comparable product of similar age and value without prejudice to the Client in terms of the remaining portion of the Factory Warranty or Maintenance Plan, or;

- Offer to purchase it from the Client at the original invoiced price less 20%, less an additional 1.25% per month depreciation since the date of delivery or;

- Offer to trade it in on a new, functionally-comparable product at the original invoiced price less 17.5%, less an additional .75% per month depreciation since the date of delivery.

In the event of a software package which is still covered by the Maintenance Plan becoming obsolete I-Cube shall reserve the right to either:

January 2008


- Replace it with a new, functionally-comparable package of similar functionality without prejudice to the Client in terms of the remaining portion of the Maintenance Plan or;

- Offer to purchase it from the Client at the original invoiced price less 20%, less an additional 1.5% per month depreciation since the date of delivery or;

- Offer to trade it in on a new, functionally-comparable package at the original invoiced price less 19%, less an additional 1.25% per month depreciation since the date of delivery.

No user support, repairs, updates or upgrades will be provided whilst any default exists in respect of terms of payment or whilst any dispute exists in respect of outstanding payments including disputes related to interest due as a result of late payments. The Client should contact I-Cube in writing prior to the placing of orders should the meaning or implication of any aspect of this Factory Warranty and Maintenance Plan be unclear or not fully understood, failing which it shall be assumed that the Client is fully au-fait and in agreement with the above terms and conditions and shall: The Maintenance Plan in respect of hardware is transferable on condition the existing Client provides I-Cube with the name and postal address of the new owner in writing within 28 days after transfer of ownership. The Maintenance Plan in respect of software is not transferable. HTSOL and the local partner, I-Cube provides a 7 year support program. Free e-mail, telephone, remote login and live chat support is provided. Maintenance will be billed in advance, once per month. Maintenance covers routine events and does not include additional training of new staff. New staff will be trained at the initial rate. All acts of god and vandalism will be billed per hour and not included in the routine maintenance. Maintenance assumes a always on, real time link to all the computers and network devices. CERTIFICATION

January 2008


Compliance Documentation Safety and Quality Program

The objectives and scope of the Quality Program are to establish standard procedures that provide a reliable and maintainable system that will ensure quality for all of the company’s products.

The Quality Program will apply to all software, hardware and vendor supplied products developed and/or supplied by the company, during the development stage, delivery to customer, and following product life cycle.

Certifications

" ISO 9001:2000

" UL, CE, GS, TUV, IEC60825-1, FCC15

January 2008


WEEKLY MAINTENANCE SCHEDULE The following items are checked on a weekly basis:

- All camera sun shields and covers. If missing these are replace. - All camera lens and glass for any obstructions / dust. If dirty these

are cleaned. - Communication latency between all sites; - Bandit alarm is checked at each site - The location of the camera focal point and field of view. If out of

focus or if the housing / camera lens has moved, this is returned to that required.

- The trigger loops or lasers if present. If not present, the unique location devices.

- The PC’s are checked for a wide range of items, including: o Space used and remaining o Response time o Memory utilisation o Ability to connect to all cameras and other computers o Ability to automatically process video allocated to other

PC’s o See Monitor running o See Cleaner running o See Data working o Monitors, keyboards, mice and case are cleaned o Other routine tasks as required

- The alternative communication routes are tested for automatic redundancy. o Fibre working o Wireless working o GPRS / 3G / EDGE working

- Please see the APPENDIX for the complete list of weekly tasks, which will be performed by the support and maintenance personnel.

January 2008


SOFTWARE MAINTENANCE All software upgrades will be provided free for the 1st year. After the 1st year software maintenance will cost 15% of the purchase price of the software. If the software maintenance option is not selected this can be purchased when required at market prices.

SPARES In order to ensure optimum uptime an as part of the maintenance programme the required spares which I-Cube will keep in Durban are:

2.00 SWI21 SeeWay System Includes: IP LPR

2.00 ANPR Cameras with mounting, IR & Acc – COLOUR

1.00 P4, 3.4GHz, 2048MB RAM, Windows XP

1.00 Camera mounting poles and acc § 12 Poles

SW for Ave Speed Measurement & LPR 2.00 DLL for LPR per PC

DELIVERY PERIOD - The period within which deliveries will be made: Initial order: One week for existing software (LPR & ASD), three weeks for hardware which is in stock, longer for items which are not in stock, 4 weeks for the solution proposed and longer periods for custom developed software. Subsequent orders: One week for existing software (LPR & ASD), three weeks for hardware which is in stock, longer periods for items which are not in stock or require custom developed software. GUARANTEE - 3 year guarantee on software. Hardware carries a one year guarantee.

January 2008


OPTIONS: LINK TO SAPS STOLEN VEHICLE DATABASE

RE: The delivery of a service providing a link to the Tsohle Unicode vehicle theft database for Durban Metro. This database is updated daily by the SAPS, and is the only officially authorised and supported service available in South Africa. Please note that supply of this service to Durban Metro needs to be authorised by the South African Police Service, which we will assist in obtaining on behalf of the Metro. This is in accordance with our contractual agreements with the SAPS. The elements of the quotation are: Online Interface from cameras at Durban Metro sites [3 simultaneous sites] to Tsohle-Unicode Vehicle Information System On line Interface for manual enquiries by Durban Metro members from computers and hand held devices at these sites [3 simultaneous sites] This on line connectivity entails: Configuration, installation and utilisation of a connection to our server at our computer centre, inclusive of a firewall. This does not include providing the physical connection such as 3G/ADSL/Diginet etc. A secure network interface Project specific development Telephonic support [working hours] Initial installation of the three sites, travel, accommodation and subsistence charges excluded. Our System can provide an MIS report & audit on all transactions undertaken by the Durban Metro if you so require This quotation does not include on site support. The equipment required for sites is excluded from the quotation, we understand that the appointed service providers will make provision for this in their quotations. The monthly fee does not limit the number of transactions The monthly fee does not include the 3G/ADSL/Broadband etc network charges and infrastructure in order to connect to our computer centre. This is the responsibility of Durban Metro and their appointed service providers.

January 2008


This is a monthly charge which is based on a minimum contract of one year. We anticipate that once the system is proven after the first pilot, that an agreement will be signed between yourselves and our company. We will require the formulation of the necessary Confidentiality agreements between Durban Metro, the service providers and Tsohle-Unicode to ensure the security of the data, as required by our SAPS agreement. The monthly Fee based on a minimum of a one year contract, excluding VAT is R9,300-00 [Nine thousand three hundred rand only].

COMPANY OVERVIEW

1 About Tsohle-Unicode Vehicle Information Systems (Pty)

Ltd

1.1 Introduction Driven by perceived market needs the Tsohle-Unicode Vehicle Information System was launched in 1993. Motivated by: • The high incidence of motor theft; • The low recovery rate by the rightful owners and a low conviction rate; • The need for information as experienced by the Short Term Insurance

Companies and fleet operators and • The need for a gateway through which the SAPS and the private sector could

exchange vehicle theft & recovery data, claims data and title holder data, on line, through a secure gateway that is fully compliant to SAPS security. Other requirements were a chain of evidence and private sector institutional confidentiality, privacy and security requirements.

January 2008


With the full support of the South African Insurance Association and the majority of its members and the full participation of the SAPS, Tsohle-Unicode launched the first version of its unique stolen and recovered vehicle on-line data service. Tsohle-Unicode was the first Private / Public sector Partnership [PPP] in the new South Africa with a total investment by various shareholders of approximately R24m. Subsequently Tsohle-Unicode entered into a ten year contract with the SAPS where in return for bulk SAPS data on stolen and recovered vehicles, Tsohle-Unicode provides the SAPS, for free within the PPP, with the following: • The Tsohle-Unicode SAPS / Private sector Gateway and data warehouse. The

Tsohle-Unicode data base is the most comprehensive vehicle theft and recovery and insurance vehicle theft claim data base in South Africa more so than the SAPS and the Insurance companies data bases;

• Sophisticated on line data base investigation tools; • A Data Integrity partner for the Vehicle Circulation System; • The Tsohle-Unicode designed and implemented Border Gate Vehicle &

Passenger Verification & Logging System – Software, Hardware, Training and maintenance;

• Sophisticated on line data base management & exception reports that assist the SAPS in combating cross border crime and internal tampering of their systems;

• The electronic upload of private sector clean & verified title holder information;

• Border Post Business Process Consulting and • Investigations support to field operatives of both the VCI and Border Police. As a result both the private sector and the SAPS are benefiting from this partnership in the battle against motor theft related crimes including fraud.

In addition, Tsohle-Unicode currently provides SAPS stolen vehicle data to :

• The motor industry • The short term insurance industry • JMPD • The vehicle rental industry

Tsohle-Unicode has become an integral and indispensable part of the above businesses and organisations; clients experience the benefits of having information available at their fingertips which previously only came to light after costly investigations. The benefits derived from this online service have played a significant role in the reduction of the very costly problem of fraud in vehicle sales and claims. Tsohle-Unicode has in the past few years, and continues to do so, produce, substantial financial benefits for our clients running into the tens of millions of Rand per annum. Our clients have proved over and over again that Tsohle-Unicode is an excellent investment to make.

January 2008


The SAPS, on the other side of the coin, have benefited in a tangible way, through this innovative and ground breaking initiative, which provides a secure and dependable gateway, and of course not forgetting the assistance rendered by Tsohle-Unicode in the prevention, detection and combating of cross border crime and the management of members at the ports of entry. One of Tsohle-Unicode’s foundations is ongoing innovation and new product / application development. This has assisted Tsohle-Unicode to maintain its leadership position in the market. Of recent, among other innovations and initiatives, Tsohle-Unicode has provided integration of the Claims administration systems of the Insurers with the Tsohle-Unicode system, on line. The advantages to the clients and new services offered by Tsohle-Unicode are very significant, obviously positively affecting income. Additionally Tsohle-Unicode has concluded a contract with another leading service provider to the financial and retail motor industry, which provides the Tsohle-Unicode services to the finance sector and financial sector information to the SAPS if and when required. The impact of this will be substantial on the finance industry and the SAPS. Another new innovation is the expansion of our database with the addition of Data Dot information for all dotted vehicles. This information will be made available to all subscribers and users of the database.

Tsohle-Unicode have recently been appointed the industry preferred supplier of bulk SAPS data under the auspices of the Business Against Crime [BAC], by the totality of the private sector involved in the manufacture, retail sales, financing, insurance, and hire of motor vehicles in the RSA. Recently the contract with the SAPS for the supply of bulk data was renewed for a further 5 years.

We continue to strive in providing excellent on line, secure and specialized strategic services to both the SAPS, law enforcement agencies and the private sector subscribers and users of the system.

1.2 BEE Tsohle-Unicode entered into the BEE process as of the 1st of July 2005 by allocating 20% of its shares to Zonkizizwe Investment Holdings as a first phase with a second phase plan to increase the BEE shareholding to 35%. Tsohle-Unicode has concluded the renewal of its PPP contract with the SAPS providing a strategic service to law enforcement with service that includes skills transfer, training and an expansion of the system to the state.

January 2008


Financial Offering The offering is provided as a capital amount, a rental option with a performance based calculation plus an option for a profit share solution. This option allows the Ethekwini Traffic Authority to purchase the ASD LPR equipment and software with no additional fees required going forward, other than the indicated monthly operating costs. Software configuration and training is included, allowing the Ethekwini Traffic Authority to set up and operate the LPR enforcement zone without any additional requirements.

The total amount, including VAT is R 1, 994,713.15 The items to be provided by the Ethekwini Traffic Authority are detailed below. I-Cube requests an establishment fee of 50%, with 20% due once the equipment is on site and 20% due once the system is operational. The remaining 10% will be retained until the end of the 1st year, if the system performs within SPEC. I-Cube will supply the following: ITEM NO QUANTITY PRODUCT DESCRIPTION 1 6.00 SWI21 SeeWay System Includes: IP LPR Consisting of: 6.00 130000115M15000 See Way Camera 11.5-69 Assy 12.00 070059WAY015000 CONT.ILL. WAY IR 1000 Assy 6.00 509325 T-Connector 2 6.00 ANPR Cameras with mounting, IR & Acc - COLOUR 6.00 "Vehicle Colour Capture camera Axis Vision Day/Night

January 2008


2 Megapixel 1/2"" Progressive Scan Colour CCD" 6.00 5-50mm VF A/I Video drive Lense 6.00 "VideoWise Camera Housing Medium Outdoor Aluminum Side Opening Housing, Concealed Cable Entry, Sun Shield, IP65, (L375xH117x138W). 6.00 "VideoWise Housing Bracket Indoor / Outdoor Beige, Wall Mount, Cable Managed, 10kg (Use with GL618, GL-619 Housing)" 3.00 24VAC PSU 2A 3.00 Sundries 3 6.00 P4, 3.4GHz, 2048MB RAM, Windows XP comprising of: INTEL PENTIUM Core 2 DUO E 6850 - 3.0GHZ INTEL 775 1066FSB MOTHERBOARD GIGABYTE 4-IN-1 BLACK+SILVER SYSTEMS TRANSCEND JETRAM 4GB DDR2-800 MEMORY MODULE BARRACUDA™ Series - 7200.10 SATAII Plus - 200GB x 5 6.00 580136 TBL-6822 Box+Flat Cable 6.00 550117 I/O Card 6.00 560006 Network card 8390mt 6.00 Chassis for Computer + 400W PSU 3.00 LG 19" LCD MONITOR 3.00 2 Port MOUSE KEYBOARD SWITCHER 4 6.00 "Camera mounting poles and acc 12 Poles – recommended 100 x 100 x 4,5t Galvanised With supporting gussets 10mm thick Base plate to be 12mm thick 5 12.00 Vehicle loops and feeder cables 6 12.00 NORTEC 1 Channel Vehicle detector (sensor) W/Socket 11 pin TD136 HI-SCAN English 230VAC 7 4.00 Ethernet HSDPA/3G/EDGE/GPRS WAN Router LIS.HSDPA-220P Duxbury 8 3.00 UPS Power to the cameras & IR units - 4 hrs LH3000: 1000VA Double conversion online pure sine wave UPS system with shutdown software 9 3 IP65 Housing for Field Mounted in Middle of Freeway, holds all the Switches, PCs, Surge Protection Panels and UPS devices) 10 1 eNATIS Data base link 11 4.00 508065 SWITCH SMC 8508T 8 PORT 1G switch with Power over Ethernet. 4-PoE ports 12 FIELD INSTALATION COSTS

January 2008


Containment and PSU 300.00 25mm bosal installed /m 3.00 204 Box 3.00 204 Box mounting kit 100.00 20 mm adaptaflex 8.00 20 mm adaptaflex connectors to be provided Electrical sub db installed Dirty power to be provided Electrical sub db UPS with 16way box and CB's 3.00 Sundries Video Installation 12.00 Camera installation incuding back box , rawbolts, focusing and setup 300.00 CAT6 installed 48.00 CAT6 Crimp connectors 300.00 Cable Cabtyre 3 core 1 mm Installed 100.00 Cable Cabtyre 3 core 2.5mm installed 3.00 Sundries 13 Control Room Install Costs 14 Networking Accessories 1.00 Crimping Tools (RJ45 / CAT6) 300.00 CAT6 Cable 48.00 Cat6 Connectors 15 SW for Ave Speed Measurement & LPR 3.00 DLL for LPR - 1 per PC 2.00 ASD SW per site (A-B) HTSOL LPR 550044 Average Speed Measurement Application S/W SeeData 16 1.00 SW for GUI & Control Room Fac 17 Camera PS & Surge Protection 3.00 Network Surge Protection for Network Cards, Cameras, Switches 3.00 Network Surge Protection for UPS & PCs 3.00 900508 Dehngaurd : 230 Volts surge protection 12.00 522015 Power Supply .15V/50W 18.00 550115 Adapter DC 12.00 522018 Power Supply .12V/40W 18 OTHER BANDIT Activ System

3.0 Installation 3.00 Hardware 3.00 Monitoring Contract Period 15.00 Training, per day

January 2008


APPENDIX: ADDITIONAL ASD INFO: Further details on the proposed LPR solution is provided in the following appendices and on the supplied CD. APPENDIX 1 ASD for GROUP 5 / Ethekwini Traffic Authority (PPT) – A PowerPoint introducing license plate recognition, ASD system design, showing the proposed ASD site layout, how the ASD system works and some example images of the ASD results from the N3 demos. Root directory of the enclosed CD. APPENDIX 2 See Way Manual (PDF) – This document provides a technical overview on SeeWay, a state-of-the-art vision based recognition system for high speed Roadside installations. The application is supported by a full set of optical and hardware subsystems as well as software applications and utilities. Directory of the enclosed CD: \Manuals APPENDIX 3: “Overview (PDF)” – Contains a brochure of the LPR solutions available from ASD. Root directory of the enclosed CD. APPENDIX 4: “See Lane (PDF)” – Contains a brochure of the See Lane software on which See Way is based. Root directory of the enclosed CD. APPENDIX 13: “ASD - LPR Solution for 3 sites 6 lanes (XLSX)” – Full equipment and software list, capital, rental or cost per transaction amounts Root directory of the enclosed CD.

MANUALS APPENDIX 5: “See Car DLL (PDF)” – Contains a brochure of the See Car DLL software on which See Way is based. Directory of the enclosed CD: \Manuals APPENDIX 6: “See Data (PDF)” – Contains technical information on the See Data a software service application that connects a cluster of recognition systems (such as See Lane or See Way) together by a network. Directory of the enclosed CD: \Manuals

January 2008


APPENDIX 7 See Lane Install (PDF)” – technical information on the LPR software install, operation and design. Directory of the enclosed CD: \Manuals APPENDIX 8 See Utilities (PDF) – Contains technical details of the See Utilities software describes the set of utilities that support Hi-Tech Solutions’ Seex products (such as SeeWay, SeeTruck, SeeCrane or SeeLane). These utilities enrich our products, ease the technical support and cut the time to market. Directory of the enclosed CD: \Manuals APPENDIX 9 See Lane Manual (PDF) – Contains technical details of the See Lane software on which See Way is based Directory of the enclosed CD: \Manuals APPENDIX 10 Installing Pleora software + Giga card - Contains installation details of the Pleora software Directory of the enclosed CD: \Manuals

Figure 42 LPR Recognition

January 2008


SA REFERENCE SITES APPENDIX 11: “ASD N3 RESULTS Sat Jan 06th (PDF)” – Contains the typical daily results from the N3 for a single day Directory of the enclosed CD: \ SA Reference Sites APPENDIX 12: “ASD N3 RESULTS SUN JAN 7th (PDF)” – Contains the typical daily results from the N3 for a single day Directory of the enclosed CD: \ SA Reference Sites APPENDIX 13: Axis 223M data sheet.pdf APPENDIX 14 IT WEB ASD Article 31 Oct 2006.(PDF)” – Contains details of the N3 ASD 3 month demo as covered by IT web The directory on the CD: SA Reference Sites contains images from the N3 ASD demo. The directory on the CD: SA ASD DEMOS contains working demos from:

- N3 ASHBURTON images (run PLAYER.EXE to see the demo).

- See Car Speed Demo (run RunMe.bat to see the demo of the ASD software)

- I-CUBE LPR Demo of RSA Customised Plates (run PLAYER.EXE to see the demo of colour images being recognised).

- N3 Camperdown Player EX (run PLAYER.EXE to see the demo of 380 cars

recognised at high speed).

- Hand Held Plate Demo (run PLAYER.EXE to see the demo of a hand held unit being used to recognise license plates).

- Colour LPR_Demo.wmv – Demo of the colour camera capturing and recognising license plates.

- DBN Metro CCTV Control Room – A 1 hour test of the use of LPR in combination with the existing CCTV cameras. Images of all vehicles captured.

Figure 43 ASD on the N3

January 2008


SOFTWARE Drivers: Hasp – Contains the software for the Hasp (dongle) drivers Drivers: IO Card – Contains the software for the IO card driver Drivers: Pleora Drivers – Contains the software for the Network Card driver SEEWAY: Seeway – Contains the software for the SEEWAY Software SEEWAY: Documents – Contains the documentation for the SEEWAY Software SEEWAY: Tools – SeeCal Software for the focus & live view of SEEWAY Software SEEWAY: Tools – See Cleaner – Software to remove unwanted image and log files from SeeWay SEEWAY: Tools – See Monitor – tool which is useful for installation and operation review, monitoring the status of SeeX applications, summarize the operation graphically & enable a quick access to the events log SEEWAY: Tools – See Service – Provide support for periodic application checks and version control SEEWAY: Client Applications – See Car Trap – It has a 'black' list of cars (such as stolen cars) displays the recognition events, and matches the vehicle number to the 'black' list. When a match is found, the display is flickered (in red) and a siren sound file is executed (Siren.wav) SEEWAY: Client Applications – See Lane Client – Displays a list to which items are added for each new data item received from the SeeWay server, all the data will be written to file. Each row shows another recognition result as reported by the DDE message coming from SeeWay. SEEWAY: Client Applications – See Lane Log – A recognition browser for past and current recognition results. It displays the recognition results (Vehicle #) and event data (lane#, date/time) and allows the user to view the images of previous results. SEEWAY: Client Applications – See Speaker – Announces the results through the computer's speakers.

January 2008


PRODUCT SPECIFICATIONS APPENDIX 14 Laser Detector (PDF) – Contains details of the laser vehicle detector

- ref_traffic4.pdf - Traffic_TTI2005jan.pdf - CM2_broc2.pdf - Traffic.pdf - CM_traffic_applications3.pdf

APPENDIX 15: AR80-GE80_Manual.pdf APPENDIX 16 AXIS 223M Network Camera: high performance camera, designed for demanding security installations. It delivers crisp and clear images disclosing every detail, thanks to its top quality 2.0 Megapixel progressive scan CCD sensor, Megapixel varifocal lens and advanced image processing. APPENDIX 16 Duxbury_HSDPA_WirelessRouter.pdf Always on high speed internet connectivity APPENDIX 17 Edge_Router-230M.pdf - Auto-sensing Ethernet Switch Equipped with a 4-port auto-sensing Ethernet switch. WAN type supported The router supports some WAN types, Static, Dynamic, PPPoE , PPTP ,L2TP, Dynamic IPwith Road Runner. APPENDIX 18 FW900Datasheet26-04-06.pdf – Ultra-Rugged Hand Held Unit 11th Generation Reliability Featuring a color touch screen and Microsoft® Windows® CE .NET 4.2 FW900 Choice for mission critical data collection APPENDIX 18 FP400 datasheet 17-05-06.pdf Lightweight & compact 4-inch (104mm) thermal printers that interface seamlessly with the Radix Ultra-Rugged handheld computers APPENDIX 18 FW-EL Charger 1.pdf multi-way loader charger from Radix is designed to exchange data with up to six FW900 ultra-rugged handheld computers whilst simultaneously charging their batteries. APPENDIX 19 quickbridge2_a4.pdf complete, user-installable wireless point-to-point bridging solution designed for reliable long distance and low latency voice and data connectivity. This high performance hop-in-a-box is available with 54 Mbps aggregate throughput.

January 2008


APPENDIX 19 Swith.pdf The ProSafe FS108P provides power and data from a single point, using Power over Ethernet (PoE) over a single Cat-5 cable. The eight Fast Ethernet ports can be used for any 10/100/1 000 Mbps link and four of these ports can supply industry-standard IEEE 802.3af power APPENDIX 20 UPS lh.pdf - Advanced true on-line, double conversion UPS system. APPENDIX 20 ADI Company Profile.pdf ADI International is a leading international distribution business of security solutions and services with over 205 branch locations across Europe, the Middle East, Africa and America. ADI International has over 50 years of experience in the specialist security sector. We have built our business by developing personal partnerships with our customers, providing them with best of breed security solutions and bespoke support services to meet the ever changing demands of the market. APPENDIX 21 AdleracEVRackDocument.pdf – Next generation environmental controlled racks.

January 2008


AVAILABLE ON THE ENCLOSED CD OR FROM THE I-CUBE WEB SITE (www.I-Cube.co.za) ARE: “SEE WAY DEMO” – Use the see way demo to see how the LPR software works over multiple lanes and watch as alarms are generated when the vehicle exceeds the set average speed above which alarms will be generated. “PLAYER” – Use the PLAYER.EXE to watch the cars from the N3 & M4 being recognised using the LPR DLL “SEE LANE” – Use the SEE LANE DEMO to see how the software works, enrol allowed cars, alarm on WANTED cars, see the log of all the vehicles and see a history of the vehicles.

January 2008


APPENDIX 22 – PROJECT PLAN The substantial experience I-Cube has developed from installing systems locally in KZN and South Africa will prove extremely beneficial during the limited time available to install the solution. Key to the successful installation and faultless operation is the initial design, based on a complete TCP/IP backbone, consisting of fibre (when available), wireless links and GSM connectivity. The connectivity allows any camera to connect to any computer, ensuring maximum uptime. The ability to obtain feedback from the equipment in the field in real time, allowing proactive response to any issue ensures all challenges are resolved before they escalate. Once the order is received, all suppliers will be immediately notified to continue to reserve the allocated equipment for this time critical solution. Alternative suppliers have been identified and can be contacted if required. A meeting with ETA will be arranged to discuss any modification to the system design, layout, position or if any of the options presented will be selected. A daily meeting time is requested for feedback on progress plus the ability to immediately identify any issues which might arise. If there is nothing to discuss, this should take only a few min. However, if any issue does present, all role players can be kept informed of the progress and decide on a suitable way forward. This is the ideal time for the operational staff to get involvement, so they understand the solution from an operational level. At each meeting additional reading material will be provided to the operational staff for study and prepare. A total of 10 days have been allocated for alternative design options, which will be until Monday 19th, when the onsite work will begin, assuming the electricity is in place. The systems will be pre-built before being installed, with substantial tests to limit any on site issues. This is the ideal time for the operational staff to get hands on involvement, so they understand the solution from a board level. The first items to be installed consist of the loop cutting (2M x 1M x 35 mm deep), pole mounting (4 bolts, 2 poles per site), rack (bolted to the site, 1 per site) and cable conducting (metal) – attached every meter (5 M from the rack to the camera – on both sides). Once these are in, the PC’s (2), cameras (4), UPS, air conditioner, loop detectors (4), bandit alarm, terminal blocks, HUB, modem, mouse, keyboard, monitor, switch and other items can be installed and connected. With three teams each site will be installed and operational within 2 days. Once the systems are installed, extensive tests begin. As these are all done from the control room this is the ideal opportunity to continue the on the job training of the personal who will operate the system. Each stage of the process will be extensively tested: from loop detection, multiple image capture, OCR, transfer of the data (plate, lane, date, time, etc.), loading users and those plates where an alarm should be generated. Tests will be performed using dedicated vehicles travelling at specific speeds to ensure the entire system is fully operational, including the measured distance between sites. The time critical nature of the project requires total commitment from a dedicated solution provider who has substantial local experience in providing this solution.

January 2008


ID Project Name Owner Days Start End 1-Feb 4-Feb 6-Feb 8-Feb 11-Feb 15-Feb 18-Feb 22-Feb 25-Feb 29-Feb 1-Mar 3-Mar 1-Apr 1-May0.0 Supply, Installation, Commissioning & Maintenance of: Automatic Number Plate Recognition System for Lane Violation Enforcement 394 1-Feb 1-Mar Frid Mon Wed Fri Mon Frid Mon Fri Mon Frid Sat Mon Tue Thur

1.0 Scope Definition Phase 2 1-Feb 3-Feb1.01 Receive written confirmation of order I-Cube 1 1-Feb 2-Feb1.02 Meet to discuss payment schedule I-Cube / Group 5 1 1-Feb 2-Feb1.03 Meet to discuss project plan I-Cube / Group 5 1 1-Feb 2-Feb1.04 Determine any modifications to plan Group 5 1 1-Feb 2-Feb1.05 Decide on any OPTIONS selected Group 5 1 1-Feb 2-Feb1.06 Decide on how public transport vehicles will be enrolled Group 5 1 1-Feb 2-Feb1.07 Decide on Training Start date and Venue Group 5 1 1-Feb 2-Feb1.08 Decide on daily meeting time I-Cube / Group 5 1 1-Feb 2-Feb1.09 Where will operators run the solution? I-Cube / Group 5 1 1-Feb 2-Feb

1.10 Decide on weekly Full Briefing meeting day and time I-Cube / Group 5 1 1-Feb 2-Feb

2.0 Equipment I-Cube 23 1-Feb 24-Feb2.01 Once tender awarded, E-mail & phone suppliers to confirm items I-Cube 3 1-Feb 4-Feb2.02 Confirm orders and deliver dates I-Cube 4 4-Feb 8-Feb2.03 Swtich to alternative souces if delivery problems I-Cube 3 8-Feb 11-Feb2.04 Moitor the status of the equipment I-Cube 20 11-Feb 2-Mar2.05 EQUIPMENT DELIVERY Group 5 20 11-Feb 2-Mar

3.0 Software Development (if required) I-Cube 23 4-Feb 27-Feb3.01 Define software selection criteria I-Cube 3 4-Feb 7-Feb3.02 Develop software selection questionnaire I-Cube 3 7-Feb 10-Feb3.03 Develop Statement of Work I-Cube 5 10-Feb 15-Feb3.04 Evaluate proposal ETA 5 15-Feb 20-Feb3.05 Select Software Required ETA 5 20-Feb 25-Feb

4.0 Public Transport Vehicle Enrolment I-Cube 110 4-Feb 24-May4.01 Determine which vehicles are allowed to use the lanes ETA 10 4-Feb 14-Feb4.02 Determine confirmation criteria ETA 7 14-Feb 21-Feb4.03 Set up numerus means where by vehicles can be enrolled I-Cube 20 21-Feb 12-Mar4.04 Enrol via SMS if selected I-Cube 100 21-Feb 31-May4.05 Enrol via E-Mail if selected I-Cube 100 21-Feb 31-May4.06 Enrol via Web Site if selected I-Cube 100 21-Feb 31-May4.07 Enrol via Phone if selected I-Cube 100 21-Feb 31-May4.08 Enrol via Hand Held unit if selected I-Cube 100 21-Feb 31-May

5.0 Build Components I-Cube 10 11-Feb 21-Feb5.01 Check PC is operational I-Cube 5 12-Feb 17-Feb5.02 Install IO card I-Cube 1 12-Feb 13-Feb

5.03 Install SEEWAY Software I-Cube 1 12-Feb 13-Feb

5.04Install Ethernet HSDPA/3G/EDGE/GPRS WAN Router LIS.HSDPA-220P Duxbury I-Cube 1 13-Feb 14-Feb

5.05 Test Comms on all 6 PC's I-Cube 5 14-Feb 19-Feb

5.06 Connect 8 PORT 1G switch with Power over Ethernet. 4-PoE ports I-Cube 1 14-Feb 15-Feb5.07 Set PC's IP address I-Cube 1 14-Feb 15-Feb5.08 Remove WAN router I-Cube 1 14-Feb 15-Feb5.09 Test Comms on all 6 PC's I-Cube 1 14-Feb 15-Feb5.10 Connect Cameras I-Cube 1 15-Feb 16-Feb5.11 Test image capture I-Cube 1 15-Feb 16-Feb5.12 Check recognition I-Cube 1 15-Feb 16-Feb5.13 Confirm LPR data sent via network I-Cube 1 15-Feb 16-Feb5.14 Confirm LPR images sent via network to ETA I-Cube 1 15-Feb 16-Feb5.15 Confirm automatic shutdown and reboot I-Cube 2 15-Feb 17-Feb

6.0 Site Install I-Cube 6 7-Feb 13-Feb6.01 Meet with ETA to identify stakeholders involved in placement All 1 7-Feb 8-Feb6.02 Invite required stakeholders to meeting ETA 2 8-Feb 10-Feb6.03 Meet with required stakeholders to confirm placement All 2 10-Feb 12-Feb6.04 Obtain permission from required stakeholders work on site ETA 5 12-Feb 17-Feb6.05 Install electricty on site Group 5 3 7-Feb 10-Feb6.06 Obtain written clearance from Municipality for cutting loops I-Cube 3 7-Feb 10-Feb6.07 Loop cutting I-Cube 3 17-Feb 20-Feb

7.0 On Site Trouble Shooting I-Cube 10 17-Feb 27-Feb7.01 This time has been allocated for any unexpected issues All 9 17-Feb 26-Feb7.02 As problems appear they will be swiftly resolved All 5 17-Feb 22-Feb7.03 The daily meeting will provide feedback for this progress I-Cube 10 17-Feb 27-Feb

8.0 Control Room Install ETA 3 1-Feb 4-Feb8.01 Where will the computers be installed ETA 2 4-Feb 6-Feb8.02 Design considerations of the venue ETA 5 6-Feb 11-Feb

9.0 On Site Tests I-Cube 2 20-Feb 22-Feb9.01 LPR BW image capture for Site 1 - 6 I-Cube 1 20-Feb 21-Feb9.02 LPR Colour image capture for Site 1 - 6 I-Cube 2 20-Feb 22-Feb

9.12 LPR BW image recognition for Site 1 - 6 I-Cube 2 20-Feb 22-Feb0.10 LPR Colour image recognition for Site 1 - 6 I-Cube 2 20-Feb 22-Feb

0.20 LPR BW image recognition for Site 1 - 6 (NIGHT) I-Cube 2 20-Feb 22-Feb1.3.1 LPR Colour image recognition for Site 1 - 6 (NIGHT) I-Cube 2 20-Feb 22-Feb

1.3.1 LPR BW image stored for Site 1 - 6 I-Cube 2 20-Feb 22-Feb1.3.1 LPR Colour image sored for Site 1 - 6 I-Cube 2 20-Feb 22-Feb

10.0 Control Room Tests I-Cube 2 22-Feb 24-Feb10.01 LPR BW image data transfer for Site 1 - 6 I-Cube 2 22-Feb 24-Feb10.02 LPR Colour image data transfer for Site 1 - 6 I-Cube 2 22-Feb 24-Feb

10.03 LPR BW image transfer for Site 1 - 6 I-Cube 2 22-Feb 24-Feb0.01 LPR Colour image transfer for Site 1 - 6 I-Cube 2 22-Feb 24-Feb

1.3.1 LPR BW data ALARM for Site 1 - 6 (NIGHT) I-Cube 2 22-Feb 24-Feb1.3.1 LPR Colour data ALARM for Site 1 - 6 (NIGHT) I-Cube 2 22-Feb 24-Feb

1.3.1 Determination of the distance between all East Bound sites I-Cube 2 22-Feb 24-Feb1.3.1 Determination of the distance between all West Bound sites I-Cube 2 22-Feb 24-Feb1.3.1 LPR BW ASD ALARM for Site 1 - 6 I-Cube 2 22-Feb 24-Feb1.3.1 LPR Colour ASD ALARM for Site 1 - 6 I-Cube 2 22-Feb 24-Feb

11.0 Hand Over Tests I-Cube 2 25-Feb 27-Feb11.1 Number plate recognition at low speed I-Cube 1 25-Feb 26-Feb11.2 Number plate recognition at medium speed I-Cube 1 25-Feb 26-Feb11.3 Number plate recognition at high speed I-Cube 1 25-Feb 26-Feb11.4 Number plate recognition at night I-Cube 1 25-Feb 26-Feb11.5 Speed Violation Detection I-Cube 1 25-Feb 26-Feb11.6 Automatic detection of unauthorised vehicles I-Cube 1 25-Feb 26-Feb11.7 Automatic detection of black listed vehicles I-Cube 1 25-Feb 26-Feb11.8 Automatic alarm on detection of stolen vehicles I-Cube 1 25-Feb 26-Feb11.9 Colour Photographioc Evidence I-Cube 1 25-Feb 26-Feb12.0 Link to selected Databases I-Cube 25-Feb 25-Feb12.1 Traffic Engineering Data Acquisition I-Cube 1 25-Feb 26-Feb

12.0 Training I-Cube 9 4-Feb 13-Feb12.1 Follow training schedule as detailed in proposal I-Cube 2 13-Feb 15-Feb12.2 Training hours per day ETA 1 13-Feb 14-Feb

13.0 Spare Parts I-Cube 7 14-Feb 21-Feb13.1 Recommended Spare Parts be be confirmed I-Cube 1 21-Feb 22-Feb13.2 Orders of Spares I-Cube 2 22-Feb 24-Feb

14.0 Support ETA 6 14-Feb 20-Feb14.1 Develop suitable selection criteria ETA 2 14-Feb 16-Feb14.2 Identify 4 people from ETA / Durban Metro ETA 2 14-Feb 16-Feb14.3 Operations Manual I-Cube 2 20-Feb 22-Feb14.4 Mainteneance Manual I-Cube 2 22-Feb 24-Feb

15.0 Repair Procedure ETA 4 14-Feb 18-Feb15.1 Training on all aspects of the solution ETA 2 18-Feb 20-Feb15.2 Identify 4 people from ETA / Durban Metro to be traine ETA 2 20-Feb 22-Feb

Supply, Installation, Commissioning & Maintenance of: Automatic Number Plate Recognition System for Lane Violation Enforcement & Speed Violation Detection through Average Speed Correlation

Figure 44 ASD PROJECT PLAN

January 2008


TO BE PROVIDED BY CLIENT The following, non‐exclusive, list of items would be required from ETA in order for the project to proceed within the time frame required (29 days). If for any reason the order is delayed, the project will be delayed for an unknown amount of time, not relating to the time the order was delayed. A clean, consistent, source of Electricity is required at all the sites in the field. Delay of the provision of the electricity beyond that detailed in the project plan will delay the launch of the project. Permission to work in the areas designated would be required from the relevant authorities. Any delay in obtaining the required permission would result in an unknown delay in the project. The proposed solution will operate automatically however if ETA are going to ensure the system operates to the best ability, trained operators are required. The training period as detailed should be followed. The project plan as detailed should be followed in order to ensure the project is operational within 29 days. Any change to this project plan will result in extended delays. Viewing software for the public for violations is not provided and is not part of the solution being offered. This can be provided after suitable discussion. Off site data storage and backup is a crucial aspect of a project of this nature. It has been assumed that ETA will take care of this. If not, a suitable solution will be resolved with ETA. For ASD to be implemented a survey of the shortest distance between the two points is required. It is assumed Group 5 or ETA will provide this. If not, I-Cube can provide a fee for this service. Connection to and User Access to NATIS Interface Server For the NATIS interface application to function correctly, a connection to and user access rights for the NATIS system supplied by National Department of Transport is required. This connection and access right is provided by NDOT to authorities, municipalities, metros, provincial government, etc on application. I-Cube will assist with the procedural work for submission of the application on behalf of Ethekwini Transport Authority.

January 2008


January 2008


Supply, Installation & Maintenance of Automatic

Number Plate Recognition (ANPR) Equipment

APPENDICES

&

CD

Submitted by:

Date: JANUARY 2008

To:

January 2008


AVERAGE SPEED DETERMINATION

A new speed determination system is now available that measures vehicle speed, not based on a singular point (as most other methods do) but rather on the length of the route, so it slows down the traffic along the entire route rather than in specific points which are quickly known to drivers. Rather than receiving a fine for speeding at a specific spot one would be tracked over a few kilometres, allowing a more “democratic” fine to be issued. Key to this solution are the license plate recognition cameras installed above traffic lanes, which automatically captures all vehicles (not just speeding vehicles), recognizes the license plate (or records if there is not one present), and records the plate and date and time. The recognition data is reported by messages through a TCP/IP network to a central computer, which matches the pairs and calculates the average speed by the time that passed travelling between the points. The image below indicates a vehicle being captured at SITE A and SITE B, in this example 8.63 KM apart. The speed limit in this section is 100 KM, while the taxi depicted was measured at a very healthy 119 KM/H. Due to the substantial backend databases, it is possible to be informed automatically if the vehicle has been speeding every day, not just then. The technology curbs speeding through automatically capturing every vehicle, provides the evidence in multiple images; covers all lanes and operates 24 hours a day (using invisible Infra-Red illumination). It is possible to set up a real time system looking at stolen vehicles and outstanding warrants using the same cameras. The system can also be connected to roadside variable message traffic signs that can alert the drivers in real time on their speeding violation, immediately changing driver behaviour for the better. The biggest advantage for the driver is that the violation detection is not based on a singular point but rather on the length of the route.