the innovative faculty - wydział elektroniki, … the innovative faculty for innovative...

The Innovative Facultyfor Innovative Technologies

Gdańsk University of Technology

Faculty of Electronics, Telecommunications and Informatics

2 T h e I n n o v a t i v e F a c u l t y f o r I n n o v a t i v e T e c h n o l o g i e s

The Faculty at a glance• 16 departments• 4 fields of studies• 3600 students• 500 graduates each year• 20 doctorates each year• 200 researchers, incl. 20 Full Professors• 50 running research projects• 150 cooperating companies

Laboratories• Advanced Computer Animations Lab• Algorithms and System Modelling Lab• Anechoic Chambers• Audio Acoustics Laboratory• Automatic Control Lab• Biomedical Engineering Lab• Computer Architecture Lab• Computer Communications Lab• Computer Networks Lab• Decision Systems Lab• Displays and Colorimetry Lab• Geoinformatics Lab• Ground Satellite Station Lab• Hydroacoustics Testing Laboratory• Immersive 3D Visualization Lab • Industrial Robots Laboratory• Innovative Materials and Devices Lab (Clean-room)• Intelligent Interactive Systems Lab• Laboratory for Integration of Automation Systems • Laboratory of Integrated and Programmable Circuits• Marine Electronic Systems Lab• Metrology Lab and Optoelectronics Lab• Microelectronic Systems Lab• Microwave and Antenna Engineering Lab• Microsoft Modern Lab• Mobile Devices Lab• Multimedia Systems Lab• Optical Coherence Tomography Lab• Radiocommunication Systems and Networks Lab• Software and Knowledge Engineering Lab• Teleinformation Networks Lab

Participation in European Research Area• Horizon 2020• EU Framework Programmes• COST• Eureka• Artemis• Norway Funds• Tempus

The Faculty at a glance• 16 departments• 4 fields of studies• 3600 students• 500 graduates each year• 20 doctorates each year• 200 researchers, incl. 20 Full Professors• 50 running research projects• 150 cooperating companies

Laboratories• Advanced Computer Animations Lab• Algorithms and System Modelling Lab• Anechoic Chambers• Audio Acoustics Laboratory• Automatic Control Lab• Biomedical Engineering Lab• Computer Architecture Lab• Computer Communications Lab• Computer Networks Lab• Decision Systems Lab• Displays and Colorimetry Lab• Geoinformatics Lab• Ground Satellite Station Lab• Hydroacoustics Testing Laboratory• Immersive 3D Visualization Lab • Industrial Robots Laboratory• Innovative Materials and Devices Lab (Clean-room)• Intelligent Interactive Systems Lab• Laboratory for Integration of Automation Systems • Laboratory of Integrated and Programmable Circuits• Marine Electronic Systems Lab• Metrology Lab and Optoelectronics Lab• Microelectronic Systems Lab• Microwave and Antenna Engineering Lab• Microsoft Modern Lab• Mobile Devices Lab• Multimedia Systems Lab• Optical Coherence Tomography Lab• Radiocommunication Systems and Networks Lab• Software and Knowledge Engineering Lab• Teleinformation Networks Lab

Participation in European Research Area• Horizon 2020• EU Framework Programmes• COST• Eureka• Artemis• Norway Funds• Tempus

The Innovative Facultyfor Innovative Technologies

www.eti.pg.edu.pl

Faculty of Electronics, Telecommunications and Informatics

Dean’s word . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6

Active Dynamic Thermography for Quantitative Skin Burn Diagnostics . . . . . . . . . . 8

AEGIR – Asynchronous, Autonomous and Ground-Based Radiolocation System . . . . 9

Analog Sub-Milliwatt CMOS Image Sensor with Pixel-Level Convolution Processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10

Auditory-Visual Attention Stimulator . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11

Automatic Video Event Detection Software . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12

CongloS – A System for Managing Contextual Knowledge Bases . . . . . . . . . . . . . . 13

Control and Energy Management System for Heating and Cooling of Buildings . . . . 14

Copcams Positioning System. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15

Dipping Sonars for Detection and Tracking Submarines . . . . . . . . . . . . . . . . . . . . 16

Emotion Monitor . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17

Friendly Applications for Behavioural Therapy of Autistic Children . . . . . . . . . . . . . 18

Immersive 3D Visualization Lab . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19

Indoor Positioning System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .20

Intelligent System of Decision-Making . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21

IP-Based Multifunctional Communication System (MCS-IP) . . . . . . . . . . . . . . . . .22

Laboratory of Mobile Wireless Technologies. . . . . . . . . . . . . . . . . . . . . . . . . . . .23

Long-Range Active Sonars for Anti-Submarine Warfare . . . . . . . . . . . . . . . . . . . .24

Library for Acceleration of Multiple-Precision-Arithmetic Computations . . . . . . . . .25

MERPSYS – Modeling Efficiency, Reliability and Power Consumption of Multilevel Parallel HPC Systems Using CPUs and GPUs. . . . . . . . . . . . . . . . . . . . .26

Medium-Range Mine Counter-Measure Sonars . . . . . . . . . . . . . . . . . . . . . . . . . .27

Mine Counter-Measure Side-Scan Sonars . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .28

Multi Component Gas Analyzer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .29

NOR-STA – A Tool Supporting Applications of Evidence-Based Arguments . . . . . . . .30

Object Re-Identification Application for Multi-Camera Surveillance Systems . . . . . . 31

Object Tracking and Automatic Master-Slave PTZ Camera Positioning System . . . . .32

Optimization and Graphics – Integrated Numerical Optimization with 3D Graphics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .33

Table of Contents

Passive Acoustic Radar. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .34

Passive Anti-Submarine Warfare Towed-Array Sonars. . . . . . . . . . . . . . . . . . . . . .35

Personalized Healthcare Solutions for Ambient Assisted Living . . . . . . . . . . . . . . .36

Polarization-Sensitive Optical Coherence Tomography with Spectroscopic Analysis. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .37

Radio Frequency Trajectory Monitoring. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .38

Raman Modular System with Fibre-Optic Probes for Remote Monitoring of CVD Processes. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .39

SART-2 – Biometric Security System for Mobile Workstations . . . . . . . . . . . . . . . .40

SchematicLab for Designing Electronic Printed Circuit Boards . . . . . . . . . . . . . . . . 41

Sensor Network for City Traffic Monitoring . . . . . . . . . . . . . . . . . . . . . . . . . . . .42

Sensor Positioning System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .43

SMOL – Dedicated Domain Language and Simulation Platform . . . . . . . . . . . . . . .44

Sound Recognition Service – A Supercomputer Service Able to Detect, Classify and Localize Threatening Acoustic Events . . . . . . . . . . . . . . . . . . . . . . .45

Street Traffic Radar . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .46

System for Creating Dynamic Maps of Noise Threats Employing Grid Computing . . .47

System for Geo-Referencing And Integration of the Spaceborne and Airborne Real Time Imagery . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .48

System for Remote Monitoring of Position of Persons in Indoor Environment – SALON . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .49

System Supporting Speech Perception for Special Educational Needs of Schoolchildren . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .50

The Interactive Eyeglasses for Mobile, Perceptual Computing . . . . . . . . . . . . . . . . 51

Video Event Recognition System with Enhanced Privacy Protection . . . . . . . . . . . .52

Virtual Whiteboard . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .53

Versatile Real Time Vector Based Electronic Map Update System for Mobile Devices . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .54

VisRobot – 3D Mapping with Variable Stereo Baseline . . . . . . . . . . . . . . . . . . . . .55

Voice Maps – System Supporting Independent Movement of the Blind . . . . . . . . . .56

YouArchive.net – Web-Based Audio Restoration System (Online Sound Restoration System for Digital Library Applications) . . . . . . . . . . . . . . . . . . . . . .57

WeatherSense – Numerical Weather Prediction for Poland . . . . . . . . . . . . . . . . . .58

Wireless Surveillance System Module . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .59

Photos . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .60

The Faculty of Electronics, Telecommunications and Informatics (ETI) educates about 3,500 students in four fields of studies: Informatics, Electronics & Telecommunications, Control Engineering & Robotics, and Biomedical Engineering. We are the largest faculty in Northern Poland in the area of modern telecommunications and information techno-logies, employing nearly 200 researchers and lecturers, which includes some 45 Profes-sors and Doctors of Science. For many years we have retained a high scientific standing, documented by the category “A” according to the Ministry of Science and Higher Educa-tion’s classification system, and by being entitled to confer a DSc (Habilitation) degree in four disciplines: Electronics, Telecommunications, Informatics and Biocybernetics & Biomedical Engineering, as well as a PhD degree in Automatics & Robotics.

The Faculty has an extensive research and didactic infrastructure at its disposal. A few year ago a new (and the Faculty’s second) building was made available, serving prima-rily didactic purposes – it houses laboratories, lecture and auditorium halls comprising a total of about 1550 seats, as well as a student-friendly Faculty office. There is also the Tri-City Academic Computer Centre, called by its Polish acronym “TASK”, with one of the fastest supercomputers in Europe, as well as a state-of-the--art library and reading room. There are many extensively equipped research and didactic laboratories. Two anechoic chambers are used for acoustic research and antenna measurements. A one of the few in Poland earth satellite station for research is installed on the roof of Building A of ETI. A modern laboratory of industrial robots funded from European funds was opened in 2012. In December 2014 the Immersive 3D Visualization Lab was opened. This unique laborato-ry is designed to develop interdisciplinary research on virtual reality. Two didactic labs has been certified by leading global companies: Microsoft and Cadence.


7T h e I n n o v a t i v e F a c u l t y f o r I n n o v a t i v e T e c h n o l o g i e s

prof. Krzysztof GoczyłaDean of the Faculty

Graduates of the Faculty have established successful world-wide known companies. Just two prominent examples are: Young Digital Planet, which is a world leader in the field of digital educational content, and IVO Software (now owned by Amazon), who are inven-tors of the international award-winning speech synthesizer “Ivona”. A large number of the Faculty’s graduates have been very successful abroad. The most prominent example is Prof. Tomasz Imieliński, co-founder of data mining, the world’s most cited Polish com-puter scientist.

The Faculty of Electronics, Telecommunications and Informatics at Gdańsk University of Technology is a modern academic centre harmoniously combining advanced research and attractive education with active cooperation in the industrial environment. Within the framework of the latter, the Faculty initiated the formation of the Pomeranian ICT Cluster “Interizon”, which integrates over a hundred business partners from many fields of information, electronics and telecommunications technologies, as well as several edu-cational institutions and local government organizations. The inventions developed in our Faculty are widely known and recognized. Among them, there are computer tools for hearing, speech and sight screening tests, as wellas a range of dedicated specialized interfaces enabling paralyzed and handicapped people to use computers. An important group are the inventions that support therapy in the case of common conditions, such as speech impairment, circulatory disorders, and infantile autism. Other inventions of great practical importance are: a passive acoustic radar, a series of mobile impedance analyzers for the diagnostics of anti-corrosion coatings, a unique mobile expert system for measu-ring the motion of gaseous pollutants in the atmospheric air, a noise monitoring system, a system for detecting trace amounts of hazardous substances, a system of smart LED lamps, or a novel method of synthesis of diamond suspensions. In this booklet you will find short descriptions of some of the inventions mentioned above, as well as some ne-west ones, developed just recently.

The Faculty of Electronics, Telecommunications and Informatics is pleased to be a mo-dern and fast-developing scientific and didactic unit of such a modern technical institu-tion as Gdańsk University of Technology. We invite you to any kind of benign cooperation to meet the great challenge - the harmonious and dynamic development of the 21st cen-tury society.



Active Dynamic Thermography for Quantitative Skin Burn Diagnostics

Purpose

The concept of using thermal excitation and measurement of thermal responses is known as Non Destructive Thermal Testing (NDTT). Active Dynamic Thermography (ADT) allows non-destructive testing of bulky, multi-structure, foil or composite materials using exter-nal heat excitation and visualisation of the infrared response, showing the surface tempe-rature distribution and thermal transients. Our investigations are directed mainly towards medical applications and development of new methods of diagnostics, e.g.: non-contact evaluation of the degree of skin burn damage; evaluation of treatment procedures; evalu-ation of intra-operation procedures in cardiosurgery etc. The aim of the work was to find the relationship between figures of merit in static thermography ΔT (difference of mean values of the burn wound and of not-affected skin area temperatures) and in ADT (thermal time constants parametric images - tau) for burn classification most suitable for choosing treatment. Statistical analysis did show a high correlation between parameters: thermal time constants, ΔT, the histopathology estimation and the burn wound classification into healed and unhealed during three weeks. The study results revealed the quantitative crite-rions tau and ΔT for burn classification allowing a proper choice of burn wound treatment.

Description

Capturing of IR-images while cooling or heating allows for calculation of thermal images used for classification of regions for conservative or surgical treatment.

This figure shows ADT set with cooling applied for burn diagnostics in clinics

Contact: Prof. Antoni Nowakowski / Department of Biomedical Engineering phone: +48 58 347 26 45 / email: [email protected]


Purpose

The AEGIR system is designed to be an independent radiolocation system, that will allow you to determine locators’ positions without using any satellite navigation systems (like GPS or GLONASS systems).

Description

In the AEGIR system all ground reference stations operate in an asynchronous way, so each one uses a local oscillator to transmit localization messages. They can also receive signals from neighboring stations. Based on the received signals, a reference station de-termines the time difference between the neighboring reference stations and its own rhythm of work. The measurement results are regularly placed in the localization messa-ge. The locator receiver is responsible for the synchronization process. On the basis of its own measurements and measurements from the reference station, it estimates its loca-tion. Compared to existing solutions like Loran-C (Long Range Navigation – C), the AEGIR system resigns from a chain relationship between reference stations. In the proposed

system, there are no supervision centers for mainte-nance, which reduces operating costs and increases system reliability. The AEGIR system will be fully functional if the locator will receive signals from at least three reference stations (2D case) or four refe-rence stations (3D case). The principle of the system is under patent protection in this country and in the European Union.

In addition, the system has the advantage that in the process of estimating the position, coordinates are determined directly, without the need to assign them to the so-called positioning lines that are ne-eded in phase radiolocation systems. Therefore, the-re is no need to input a starting position and count the excess position lines that are repeated on a re-gular basis in the area of the system, and that can lead to errors in determining the correct latitude and longitude.

AEGIR – Asynchronous, Autonomous and Ground-Based Radiolocation System

Contact: Prof. Jacek Stefański, PhD, DSc / Department of Radio Communication Systems and Networks / phone: +48 58 347 15 66 / email: [email protected]

AEGIR - in Norse mythology: god of ocean


Purpose

The developed image sensor, fully integrated on a single chip and consisting of a matrix of image sensitive elements with ultra-low-power image processors, has many applica-tions in modern equipment. Such sensors, called vision chips, find various applications in robots, biomedical implants, road traffic control systems, and navigation systems. Vision chips are particularly suitable in applications where numerically-intensive early vision processing algorithms are used to smooth or sharpen images, detect edges, reduce noise, etc. The low power consumption of vision chips is of great importance for autonomous systems powered from batteries or small solar cells

Description

A new approach to design of analog ultra-low-power, medium resolution vision chips has been invented. The innovative structure of the vision chip uses a photodiode, MOS switches, and only two capacitors to create a fully functional processor, able to calculate any convolution algorithm, based on a full 3x3 kernel, in real time. The proof-of-concept integrated circuit was fabricated in 0.35 µm CMOS technology, containing 64x64 image matrix of a single instruction multiple data (SIMD) architecture. The prototype has been functionally tested and measured. The performed tests show that the developed chip is able to correctly process images using convolution algorithms with a speed up to 100 frames per second. The chip consumes less than 0.3 mW of power (less than 0.1 µW per pixel) under 3.3 V supply voltage.

Analog Sub-Milliwatt CMOS Image Sensor with Pixel-Level Convolution Processing

Contact: Prof. Stanisław Szczepański / Department of Microelectronic Systemsphone: +48 58 347 22 78 / fax: +48 58 347 23 78 / email: [email protected]

Chip microphotography Captured real image Convolution edge detection


Purpose

It is estimated that about 2% of children have undermined lateralization of the brain. The proposed solution is based on the assumption that lateralization of sight/hearing could be focused by the stimulation of those senses in an appropriate way. Features of the sys-tem will allow for the correction of, and consistent development of, children; especially in the case of children with various impairments (especially cross-dominance or dyslexia).

Description

The main idea is to perform parallel stimulation of the sight and hearing senses using digital signal processing techniques. Modification of visual and hearing stimuli is per-formed in order to focus perception of those senses by the appropriate hemisphere (by means of the lateralization profile). Sense of hearing is stimulated using the time scale modification (TSM) of speech combined with amplitude modification of speech used du-ring the training. The sight is stimulated by displaying the text of the spoken elements. Text is modified during the training, i.e. part of the text that is currently heard in the he-adphones is marked using various techniques (e.g. zooming, colouring, etc.). In the exten-ded version of the system, parameters associated with vision and hearing modification algorithms might be controlled by a gaze tracker.

Auditory-Visual Attention Stimulator

Contact: Piotr Odya, PhD / Department of Multimedia Systems phone: +48 58 347 23 01 / fax: +48 58 347 11 14email: [email protected]


Automatic Video Event Detection Software

Purpose

This product is the prototype of a video processing and event detection solution desi-gned to be applied in multi-camera surveillance systems. It detects moving objects in fixed camera streams, tracks them, classifies them, and detects user-defined events in-cluding intrusion and wrong-direction movement, as well as specialized events, such as abandoned luggage, events occurring in a parking lot (parking time and place identifica-tion, entering and leaving a parking lot, etc.), and traffic events (prohibited lane change, stopping in the middle of an intersection, etc.). All events are instantaneously reported to the system operator.

Description

The system can operate on any Windows or Linux OS PCs with digital IP cameras atta-ched. The system is highly distributed and scalable, therefore multiple servers may be employed to the processing of streams from a large number of cameras. Results of video analysis are transmitted to dedicated end user terminals by wired links, WiFi, or GPRS, including PCs and Smartphones.

Contact: Piotr Szczuko, PhD / Department of Multimedia Systemsphone: +48 58 347 29 72 / email: [email protected]

Intrusion detection example

Prohibited lane change detection Abandoned luggage detection


CongloS – A System for Managing Contextual Knowledge Bases

Purpose

To efficiently manage modular knowledge bases organized hierarchically with capabili-ties to systematize various areas of knowledge, to reflect different viewpoints, and to improve efficiency of reasoning while maintaining high expressiveness of state-of-the-art knowledge representation languages.

Description

CongloS is a system for managing modular knowledge bases organized hierarchically. Such an approach gives the designer of a knowledge base the possibility of creating a precise description of the domain of interest and, with similar means, of reuse and au-gmentation of the general knowledge contained in ontologies. In the theoretical sphere such an approach is based on the SIM model and tarset model, both developed at the Faculty. Tarset is a „unit of knowledge” which can be flexibly com-bined with other units. SIM binds these units into a tree-like hierarchy whose branches reflect different parts of the universe of discourse, described from different points of view and at different levels of detail.While solid theoretical foundations give CongloS features like soundness and complete-ness of reasoning, clever design allows it to be combined with state-of-the-art tools for ontology engineering, like Protégé and OWL-API. CongloS system is freely available for download as a set of plug-ins for the popular Protégé editor and it seamlessly augments its functionality with the abilities of creating contextual knowledge bases, visualizing their structure, and reasoning from them.

Contact: Prof. Krzysztof Goczyla / Department of Software Engineeringphone: +48 58 347 13 18 / email: [email protected] Waloszek, PhD / Department of Software Engineeringphone: +48 58 347 24 75 / email: [email protected]


Control and Energy Management System for Heating and Cooling of Buildings

Purpose

Reduction of non-renewable energy consumption in buildings requires a significant tem-perature decrease of heat sources. A new approach to transfer and distribution of heat and cool in buildings is proposed which is based on the idea of controlling the heat trans-fer process through buildings’ external walls.

Description

The software system for energy management in buildings governs the process of heat transfer through buildings’ external walls by controlling the energy supply to simple heat exchangers made of polypropylene pipes located inside the external walls of the buildings. The energy is extracted from a ground cool storage system (a cooler) and from a very low-temperature heat source (a heater to 20°C – 25°C). It allows the use of any clas-sic heating device or ground heat storage system. Moreover, heat can be supplied from modern solar collectors or PV/T panels. The system implements an innovative control method using the Fuzzy Gain Scheduling Variable. The system is founded on a sensor network, which is used for probing the heat transfer process. Specific sensors are em-ployed to measure the heating and cooling loads as well as the parameters of the applied heat and cool sources. Extraction and distribution of energy is controlled by actuators and valves working in a proportional control mode. The operating fluid has an optimal temperature and its mass flow rate carries a predicted amount of energy (heat or cool) to, or from, the heat exchangers. In this way, the system affects the heat transfer process. As opposed to traditional approaches, the indoor air temperature is not the controlled variable, but its magnitude is a result of an energy balance within the entire building, or its selected zones.The system’s functioning results in a significant reduction of total energy consumption. In particular, the temperature of heat sources can be decreased below the temperature found in most modern solutions; and significant savings in the non-renewable energy consump-tion can also be obtained (in the case of the cooling function reduced down to zero).

Contact: Prof. Zdzisław Kowalczuk, PhD, DSc, MScEE / Department of Decision Systems and Robotics phone: +48 58 347 2018/2298 / email: [email protected]


Copcams Positioning System

Purpose

Copcams Positioning System enables identification and localisation of objects in harsh environments (production lines, factories) by means of a Smart Camera.

Description

Copcams Positioning System is based on vision and radio frequency (RF) methods, which support production processes in regard to on-demand object localization, and infrastruc-ture tracking (tools, vehicles). The system relies on smart cameras having RF sensing ca-pabilities – i.e. they are able to sense passive and active RFID tags and find their position (by video and RF signals processing). Smart Cameras form a distributed system where information is processed on the device (in multicore System on Chip). The system is easy scalable by simply adding new Smart Cameras with RF sensing capabilities without ha-ving to expand the existing computing power infrastructure. Copcams Positioning Sys-tem provides added value to end-users by combining the possibilities of video and va-rious RF techniques – i.e. to notice, identify and localize objects without visual contact.

Smart Camera used for object localization Localized node attached to an object

Copcams Positioning System user interface with a localized object

Contact: Łukasz Kulas, PhD / Department of Microwave and Antenna Engineering / phone: +48 58 347 16 59 / email: [email protected]

This work has been funded by the Polish Natio-nal Centre for Research and Development (GA

number ARTEMIS-2012-1/3/2013) and by the Artemis JU (GA number 332913) as part of the

COPCAMS project (http://copcams.eu)


Dipping Sonars for Detection and Tracking Submarines

Purpose

Dipping sonars for helicopters are a new system designed for detection and tracking submarines in both active and passive modes. They are equipped with an additional gradient passive array and a meter of speed velocity distribution in water. The system was originally built as analogue sonars with the transmitting and receiving array rotated mechanically. Its modernization conducted at the Gdańsk University of Technology invo-lved designing new electronic systems in the transducer, receiver and imaging system. The dipping sonars are fully operational on Polish Navy anti-submarine warfare (ASW) helicopters and ships, meaning that they meet the strict requirements of the highest technology readiness level (TRL 9).

Description

All of the electronic systems in the transducer, receiver and imaging system are designed with a digital microprocessor, real-time technology. The on-deck transmitter generates bro-adband, frequency-modulated sounding signals using a direct digital synthesis (DDS) mo-dulator. The sonar receives echo signals from a revolving ultrasonic transducer operating in the active mode and 4 signals from hydrophones of the passive array. The pulse compres-sion technique applied in the active mode significantly improves detection performance and increases the range for detecting and tracking submarines visualized on the on-board operator console colour monitor.our monitor.

Contact: Jacek Marszal, PhD, DSc / Department of Marine Electronic Systems phone: +48 58 347 22 30 / email: [email protected]

Dipping sonar system for helicopter

Dipping sonar console

PPI presentation in the dipping sonar


Dipping sonar console

Emotion Monitor

Purpose

Emotion Monitor is a laboratory stand and software solution that enables monitoring the emotional states of a computer user. The stand allows to conduct research on human--computer interaction as well as to perform commercial studies of software products and user experience using automatic emotion recognition solutions.

Description

Description:The Emotion Monitor stand combines multiple modalities used in emotion recognition in order to improve the accuracy of affect classification. The stand is equipped with com-puters, cameras and a set of biosensors which monitor user activities and record multiple user observation channels at the same time: • physiological signals (skin conductance, respiration, electromyography, EEG, heart

rate, peripheral temperature), • video input for facial expression analysis, • behavioural observations, including keyboard and mouse usage patterns,• textual inputs for sentiment analysis,• eye tracker.The stand combines data from diverse modalities in order to obtain more reliable and accurate information on user emotions in the HCI context.

Contact: Agnieszka Landowska, PhD / Department of Software Engineering,Phone: +48 58 347 29 89 / email: [email protected] in Human-Computer Interaction Research Group, http://emorg.eu/


Friendly Applications for Behavioural Therapy of Autistic Children

Purpose

„Friendly Applications” are software solutions supporting behavioural therapy of auti-stic children. The project is held with the support of the Institute for Child Development (ICD) from Gdańsk, Poland, which uses cognitive-behavioural methods in child therapy. Our motivation to develop e-technologies supporting autistic children lies in the belief that appropriate therapy adjusted to the deficits of an individual may result in an inde-pendent adult life. The project conforms to non-profit and open source rules. As a result, anyone is welcome to use the applications in therapeutic practice and to contribute to the development of apps.

Description

„Friendly apps” is a family of software solutions for tablets with the Android operating system. The family consists of:• Friendly Plan and Friendly Plan Manager – applications for an activity-based schedu-

le method of therapy; both are already available from Google Play;• Friendly Lines – application for the development of small motor skills (hand prepara-

tion for writing activities); it will be launched by the store soon;• Friendly Words and Friendly Words Manager – applications for the development of

language understanding;• Friendly Emotions and Friendly Emotions Manager – applications for progressing

emotional intelligence;• Friendly Data (aca MROZA) – applications monitoring a child’s progress (for therapi-

sts only); server-based solution.

Contact: Agnieszka Landowska, PhD / Department of Software EngineeringPhone: +48 58 347 29 89 / email: [email protected] Anna Budzińska, Iwona Ruta-Sominka, Institute for Child Development, http://iwrd.pl/


Immersive 3D Visualization Lab

Contact: Agnieszka Landowska, PhD / Department of Software EngineeringPhone: +48 58 347 29 89 / email: [email protected] Anna Budzińska, Iwona Ruta-Sominka, Institute for Child Development, http://iwrd.pl/

Purpose

Immersive 3D Visualization Lab ensures the highest possible degree of feeling immer-sion, owing to unrestricted freedom of movement and stereoscopic 3D projection, com-bined with the least amount of equipment worn by users to provide them with the maxi-mum comfort and impression of natural activity.It can be applied in, among others:• military and homeland security training and operations planning (for the so called cyber-warriors),• industrial inspection, training and examination of complex structures,• virtual prototyping of vehicles and machines,• scientific and architectural visualization,• virtual tourism, exhibitions and museums, education,• measuring the impact of the environment on human behavior,• psychological treatment of various mental disorders and phobias,• virtual surgery and visualization of other medical procedures,• entertainment (e.g. computer games).

Description

Implementation of a mechanism of movement without changing location is carried out using a transparent sphere of 3.05m in diameter, freely rotating on the supporting rol-lers. The user is placed in the sphere through a special hatch opened from outside. The rotary transparent sphere with the user is located in the center of the cubic CAVE with edges of about 3.4m each. The CAVE consists of six acrylic flat screens

(four walls, floor and ceiling). To allow access to the CAVE, one of these screens is an au-tomatic sliding door. The rotary sphere is removable from the CAVE. This allows for testing other models of locomotion interfaces. It is also possible to use the CAVE in the typical way, without any walk simulation device, only with some handheld controller (fly stick or wand). In addition, the removed rotary sphere, enriched with a virtual helmet, can simultaneously allow for independent simulation or for distributed simultaneous simulation of both de-vices (the sphere and CAVE).The lab provides a unique facility for developing and testing interaction scenarios in va-rious fields of human activity.

Contact: Jacek Lebiedź, PhD / Department of Intelligent Interactive Systemsphone: +48 58 347 20 96 / email: [email protected]


Indoor Positioning System

Purpose

Indoor Positioning System allows to localize objects and persons inside a building, in cir-cumstances where traditional navigation systems are not efficient. The localization of objects is based on different methods (vision methods, radio frequency methods) and is available through a web application.

Description

Indoor Positioning System is based on a Wireless Sensor Network (WSN) deployed inside a building. Localization methods can use different environmental features (signals) and their properties - different characteristics associated with the propagation of radio si-gnals (RSS, ToF, DoA, etc.) or a video stream delivered from a traditional CCTV system. The system relies on measurements of various signals from the environment and different si-gnal properties, and uses advanced algorithms for data processing so that different com-ponents of the system can eliminate their weak points and improve the overall accuracy whilst simultaneously keeping infrastructure costs low. The system uses, i.a. a dedicated switched-beam ESPAR antenna.

Contact: Contact: Łukasz Kulas, PhD / Department of Micro-wave and Antenna Engineering / phone: +48 58 347 16 59email: [email protected]

The research from DEWI project (www.dewi-project.eu) leading to these results has received funding from the ARTEMIS Joint Undertaking under grant agreement n° 621353 and from the

Polish National Centre for Research and Development

Indoor Positioning System application interface

ESPAR antenna used for object localization IPS simplified architecture


Intelligent System of Decision-Making

Purpose

Intelligent System of Decision-making – ISD, based on cognitive psychology and motiva-tion theory, is a management scheme intended for controlling autonomous agents that are present in various forms of virtual/software agents, avatars, internet interlocutors, chatterbots, or bots, household appliances, unmanned ground vehicles, as well as dif-ferent stationary or mobile robots, etc. In industrial circumstances, the system may be implemented on any robotic platform equipped with a sensible set of various sensors and actuators.

Description

The system represents, on a certain level of abstraction and generaliza-tion, a coherent anthropological approach to the engineering issue of controlling autonomous robots and agents. The idea of the Intelligent System of Decision-making (ISD) is based on appropriate modelling of the human mind using the available past and modern psychological knowledge. Thus the ISD system, implementing the theory of embodied

intelligence and decision making, has been derived both from the achievements of cognitive psychology (as to information processing), motivation theory (where needs and emotions are used as a drive for the autonomous system), and several other detailed theories which concern memory, categorization, perception, and decision-making.As a consequence, we have developed a universal system which approximately imitates the way people make decisions, from an incentive to a reaction. The main mechanism of decision-making in ISD is based on the concept of needs which constitute a principal drive for any action. Needs are phenomena (and variables) pro-grammable by the user (in future, they can also be created autonomously by the agent and adjusted to operating situations). Thus, different sets of needs may be used to shape the characteristics (personality) of the agent, according to its environment and goals. The objects and events observed, as well as actions performed by the agent (namely, the-ir effects) have a definite impact on the state of the agent’s needs. Moreover, in line with the human motivation theory (emotions are one of the most important factors of human behaviour), emotions in ISD perform their function at a higher level of control than the system of needs. In our robotics applications, emotions allow to narrow down the set of possible reactions to those that are most adequate (from the viewpoint of the designer) in a current outer (ambient) situation and the internal states of the ISD system.

Contact: Prof. Zdzisław Kowalczuk PhD, DSc, MScEE / Department of Decision Systems and Robotics phone: +48 58 347 20 18, +48 58 347 22 98 / email: [email protected]ł Czubenko, MSc / email: [email protected]


IP-Based Multifunctional Communication System (MCS-IP)

Purpose

As part of a research and development project, in cooperation with the scientific-indu-strial company DGT LAB, a dispatcher distributed system, integrating both communica-tion and information functions obtained from mobile and stationary scattered informa-tion points, has been developed.

Description

The developed MCS-IP Set consists of an operator console and a universal radio controller with digital and analog radio-station units. The MCS-IP Set can be used for land, sea and air mobile operations.This set enables to setup communication connections with a wide range of supplementary services, for both mobile and stationary points, and visualize real-time or archival informa-tion on a digital interactive map.The MCS-IP Set supports a multiple wireless system which includes analog and digital solu-tions (DMR and TETRA). The set, together with other elements of the distributed system, co-operates with the following wireless communication standards: GSM, UMTS, LTE, and wired PSTN, ISDN, PDN.The visualization of information about objects observed by the distributed system can be depicted on a map or in a tabular form. The presentation of information can be configured according to the needs of the system’s operator.The MCS-IP Set has obtained all required operating certificates.

Contact: Prof. Sylwester Kaczmarek, PhD, DSc / Department of Teleinformation Networksphone: + 48 58 347 27 67 / e-mail: [email protected]. Ryszard Katulski / Department of Radiocommunication Systems and Networksphone: +48 58 347 21 08 / email: [email protected]


Laboratory of Mobile Wireless Technologies

Purpose

With the immense popularity of mobile computing devices and ubiquitous presence of diverse wireless network systems in metropolitan areas, it is evident that classical la-boratory setups used to validate communication and application solutions in such an environment can only yield a rough approximation of their real workings. The Laboratory of Mobile Wireless Technologies aims to provide a monitored testbed environment wi-thin a real-world metropolitan area, suitable for performing a wide range of experiments involving wireless and mobile IT solutions.

Description

The Laboratory infrastructure consists of about 25 installation points located across the Tri-City metropolitan area, each containing at least three WLAN (Wireless Local Area Ne-twork) interfaces of IEEE 802.11 a/g/n/ac standard, complete with external antennas for 2.4 and 5 GHz ISM bands, integrated by a centralized wireless network controller and a dedicated management system. Each installation point is capable of monitoring a radio spectrum at PHY level to allow easy interpretation of the experiment results obtained. The WLAN infrastructure is augmented with WMAN (Wireless Metropolitan Area Ne-twork) base stations located at the Faculty building, utilizing RADWIN JET and Fiber-In--Motion technologies to provide coverage of selected districts of the city of Gdańsk and the Gdańsk Bay area.

The Laboratory enables experiments in a generic working environment of the modern mobile device user, providing the best possible verification of tested mechanisms, pro-tocols, technologies, applications and systems. The combination of WLAN and WMAN access infrastructure offers a versatile network environment for mobile devices, and the locations of the Laboratory’s installation points ensure a broad range of metropolitan area conditions. The Laboratory is also a part of the PL-LAB 2020 national research ne-twork that spans a number of advanced laboratories specializing in modern technologies from Internet of Things to Cloud Computing.

Contact: Krzysztof Gierłowski, MSc / Department of Computer Communicationsphone: +48 58 347 19 65 / email: [email protected]


Long-Range Active Sonars for Anti-Submarine Warfare

Purpose

The hull-mounted anti-submarine warfare (ASW) long-range, multi-beam sonar systems with full angular range of target observation are designed for the detection, localisation and tracking of ships and other objects hidden in the water column. Prior to the moderni-sation at the Gdańsk University of Technology, all of the electronic systems were analo-gue. Today, sonars are equipped with modern visualisation and digital data transmission systems and they are fully operational on Polish Navy ships of both Soviet and American origin, meaning that they meet the requirements of the highest technology readiness level (TRL 9). Description

The long-range active ASW systems are equipped with a cylindrical acoustic antenna co-operating with the beamformer, which allows simultaneous observation of targets at all bearings around the ship. Automatic position stabilization of the antenna enables con-ducting a continuous survey of targets and determining their position with a good accu-racy even at high see states. Very high energy sounding pulses ensure a long range (up to 32 km), even in difficult propagation conditions. The system is equipped with an imaging assembly with 4 colour display screens and control panels, operated by two operators.

Long-range ASW sonar with cylindrical array

PPI display of ASW sonar in object-tracking mode

Block scheme of long-range ASW sonar system

Contact: Jacek Marszal, PhD, DSc / Department of Marine Electronic Systems phone: +48 58 347 22 30 / email: [email protected]


Library for Acceleration of Multiple-Precision-Arithmetic Computations

Purpose

Although standard 32/64-bit arithmetic is sufficient to solve most computational pro-blems, there are still problems that require higher numerical precision. Multiple-Precision Arithmetic MPA libraries are software tools for realization of computations with particular user-defined precision. You can expect that libraries MPA will play an increasingly impor-tant role in research tools in the future. Currently, MPA computations are applicable for: (i) implementation of special mathematical functions; (ii) solving ill-conditioned systems of linear equations; (iii) derivation and verification of novel formulas and theorems. Unfor-tunately, the overhead of MPA calculations can be high. Hence, a set of basic arithmetic operations in MPA is accelerated on graphics processing units (GPUs) with the use of the CUDA technology. The library is developed with the use of the standard interface compati-ble with the GNU MPA (GMP) library.

Description

Elementary arithmetic operations such as addition, subtraction, and multiplication are sufficient for many investigations requiring MPA. While the addition and subtraction of two n-digit numbers require O(n) operations, their multiplication requires O(n2) opera-tions in the standard implementation. Multiplication of two numbers is equivalent to convolution calculation which can be accelerated using the Fast Fourier Transform (FFT).

Accordingly, in the developed implemen-tation of the MPA multiplications, the co-nvolution calculations are accelerated by means of FFT performed on GPU. The ad-vantages of this method can be shown at sufficiently high precision computations.Exemplary runtimes of the developed mul-tiplication procedure (GPUMPAMUL) vs. open-source libraries (CUMP and GMP). MPA multiplications are computed for a constant size of arrays set to 1000, and va-rying precision.

Contact: Prof. Zdzisław Kowalczuk, PhD, DSc, MScEE / email: [email protected],Department of Decision Systems and Robotics / phone: +48 58 347 2018/2298,Tomasz Stefański, PhD, DSc, MScEE / email: [email protected]


Purpose

The system allows simulation of running parallel applications on large scale cluster and volunteer based systems that consist of various compute devices such as CPUs, GPUs and network interconnects. It allows prediction of the application execution time, ener-gy consumption and probability of successful execution.

Description

Goals and effects1. Creation of parametrized models of large scale systems which consist of compo-

nents such as computational (CPU, GPU) and network devices.2. Definition of models of parallel applications.3. Definition of functions that estimate the execution time, reliability and energy con-

sumption of computational and communication blocks in an application based on practical tests.

4. Implementation of a simulation environment for simulation of the execution of paral-lel applications on large scale systems. The environment consists of: client application – editor that allows modeling systems and applications as well as the simulation ma-nagement panel; hardware database (includes computational and network devices); models that define the execution times of blocks, energy consumption and reliability; simulator of execution of the aforementioned parallel applications in the system – it allows conducting simulations that return the application execution time, energy used and simulated reliability of execution.

MERPSYS - Modeling Efficiency, Reliability and Power Consumption of Multilevel Parallel HPC Systems Using CPUs and GPUs

Contact: Paweł Czarnul, PhD, DSc / Department of Computer Architecturephone: +48 58 347 25 24 / email: [email protected] / http://merpsys.eti.pg.gda.pl


Contact: Paweł Czarnul, PhD, DSc / Department of Computer Architecturephone: +48 58 347 25 24 / email: [email protected] / http://merpsys.eti.pg.gda.pl

Medium-Range Mine Counter-Measure Sonars

Contact: Jacek Marszal, PhD, DSc / Department of Marine Electronic Systemsphone: +48 58 347 22 30 / email: [email protected]

Purpose

Mine counter-measure (MCM) sonar systems are designed for searching, detecting, and localising bottom and contact mines, especially in shallow water with strong bottom reverberations and substantial deflection of acoustic wave propagation routes. The systems were originally built as analogue sonars. Its modernization conducted at the Gdańsk University of Technology involved exchanging almost all of the electronic sys-tems, resulting in modern sonar systems with good tactical and technical parameters.

Description

MCM sonars are multi-transmitting and multi-receiving beam systems designed with a digital microprocessor, in real-time technology. On the transmitting side, the RDT tech-nique of the electronically rotated beam is used, the sounding signals and beam rota-tion being performed with the direct digital synthesis (DDS) controlled by single-chip microprocessors. On the receiving side, a multi-processor DSP system is used running the algorithms of a beamformer operating in the frequency domain with the second order sampling and 14-bit resolution. Two LCD monitors are used to support the operators in detection, identification and tracking of objects.

Layered model of signal processing in the MCM sonar system

MCM sonar system

Basic display of MCM sonar


Mine Counter-Measure Side-Scan Sonars

Purpose

Side-scan mine counter-measure sonar systems use a very effective underwater acoustic method for detecting and localising motionless underwater objects. Originally construc-ted at the Gdańsk University of Technology as a completely analog system, the side-scan MCM sonars were then rebuilt with the use of modern digital signal processing and vi-sualization techniques. Today, they are fully operational on Polish Navy MCM ships, me-aning that they meet the strict requirements of the highest technology readiness level (TRL 9).

Description

Side-scan sonars are active systems designed with a digital microprocessor, in real-time technology. Multi-element ultrasonic transducers are towed behind the ship above the bottom in a so-called tow fish, with beams patterns directed diagonally towards the bot-tom, to the right and left. The echo signals from the towed transducers are converted into the digital form and sent to the on-board device using the VDSL data transmission technology. The survey results are displayed on a two-monitor operator console. The side--scan method works effectively in deep water and on the bottom (e.g. contact and bot-tom mines, shipwrecks, underwater structures), and helps with identifying the seabed topography (for hydrographic purposes – making seabed maps) on an area of several hun-dred meters wide on both sides of the sounding vessel.

Determining shipwreck location with the side-scan sonar

Side-scan sonar tow



Purpose

Low-cost, real time measurement solution for up to 10 environmental gasses’ detection and analysis.

Description

The analyzer is based on low-cost different type gas sensors. The device is an ideal solu-tion for rapid screening of environmental pollutants. Unique measurement techniques and data analysis reduce cross-sensitivity and long term sensor drift, allowing long term operation without maintenance. The device has build logging capability and the possibi-lity of remote control with GSM. Compact size and fast installation allow mobile or sta-tionary application. The dedicated software allows communication with a few analyzers.

Multi Component Gas Analyzer

Contact: Grzegorz Jasiński, PhD / Department of Biomedical Engineeringphone: +48 58 347 17 35 / email: [email protected]


NOR-STA – A Tool Supporting Applications of Evidence-Based Arguments

Purpose

To provide effective and efficient support for processes of achieving and assessing con-formance to norms and standards and for processes of analysing and demonstrating as-surance of selected quality objectives.

Description

NOR-STA is a software tool for development, management, communication and asses-sment of evidence-based arguments. NOR-STA can be used to develop and assess: • assurance cases, to demonstrate system safety, dependability, security and other

properties,• conformance cases, to demonstrate conformance with standards,• rating evaluations, to assess conformity of an organization to the requirements of

a given rating system.NOR-STA supports all parties involved in the implementation of assurance and confor-mance processes, including owners, promoters, users, auditors and consultants. It provi-des a unique on-line and mobile communication platform with dedicated services.

NOR-STA is a commercial product offered by Argevide, the GUT spin-off company. Argevide offers different models of NOR-STA licensing, including on-line services, server licences and single computer licences.

Contact: Prof. Janusz Górski / Department of Software Engineeringtel. +48 58 347 19 09 / email: [email protected]

www.argevide.com


Purpose

The motivation to create this prototype is the need to identify the same object in video streams from different cameras characterized by various recording conditions. This me-thod can be used for tracking objects moving from one camera to another, especially in case of overlapped Fields of View (FOVs). Defining of a common region in FOVs of a par-ticular pair of cameras is a starting point to the solution of the problem of objects’ re--identification. For disjointed camera views a more sophisticated approach is necessary, because the video surveillance system can contain various types of cameras with diffe-rent orientations, and illumination conditions can vary as well. The set of visual features and matching algorithms is applied in the elaborated software.

Description

The prototype works as part of a surveillance system equipped with non-overlapping cameras, making it possible to track moving objects in the case of discontinuous visual presence in the available set of cameras and under variable illumination conditions.

Object Re-Identification Application for Multi-Camera Surveillance Systems

Contact: Prof. Andrzej Czyżewski, Karol Lisowski, MSc. / Department of Multimedia Systemsphone: +48 58 347 16 36 / email: [email protected]

Multi-camera object matching

Variable visual features of objects


Purpose

This product is a prototype of object tracking and automatic pan-tilt-zoom (PTZ) camera positioning intended for multi-camera surveillance systems. It detects an object of inte-rest in a fixed camera view, tracks its movement, and automatically controls a high zoom PTZ camera to follow the object. Objects leaving the camera’s area-of-coverage are automa-tically detected and recognized in nearby cameras, thus the tracking may be continued in larger areas.

Description

The application can operate on any Windows and Linux PC with digital IP cameras at-tached: at least one fixed, and one PTZ, camera are required. It is able to record video streams, to process them, and to transmit data to dedicated terminals by wired links, WiFi, and GPRS. Besides PC-based terminals, it supports also smartphones (with Win-dows Mobile OS), providing video streaming and touch screen operation for selecting the object of interest in the video.

Object Tracking and Automatic Master-Slave PTZ Camera Positioning System

Contact: Piotr Szczuko, PhD / Department of Multimedia Systemsphone: +48 58 347 29 72, email: [email protected]

PC terminal with four FullHD displays

Automatic PTZ camera tracking the object


Optimization and Graphics – Integrated Numerical Optimization with 3D Graphics

Purpose

OPT&G is powerful and easy-to-use software integrating numerical optimization me-thods with excellent graphics. With the built-in functionalities of OPT&G, one can solve many nonlinear programming problems and promptly visualize the results. Developed as a teaching tool for students, OPT&G allows one to focus on applications rather than on programming.

Description

Basic features of OPT&G are as follows:• OPT&G is an interactive, user friendly and error-resistant software, which can be dri-

ven both by a keyboard and a mouse,• Integrated environment of OPT&G provides you with simple communication tools,

such as dialog windows, built-in editors, etc., and enables supplying data from/to other programs, files or peripheral units,

• OPT&G enables the user to easily formulate optimization problems, as well as user’s functions defined both as algebraic expressions, or Pascal or C subroutines (compiling and linking them does not require getting out of the OPT&G system),

• Various optimization methods are available for solving a wide spectrum of problems (of unconstrained and constrained nonlinear programming), where you can follow the procedures step by step, change control parameters and compare methods,

• OPT&G offers multidimensional colour graphics to visualize the objective functions, constraints and procedural steps: (a) drawing 2D-contour lines of the functions; (b) producing 3D-surface plots; all supported by specialized menus and drawing tools,

• A comprehensive user’s guide is built-in and reference sections are easily available while working in the dialog windows and menus of OPT&G.

Contact: Prof. Zdzisław Kowalczuk, PhD, DSc, MScEE / Department of Decision Systems and Robotics phone: +48 58 347 2018/2298 / email: [email protected] Rudzińska PhD / email: [email protected] Kormański PhD / email: [email protected]


Purpose

The Passive Acoustic Radar is a prototype solution that can be used for automatic detec-tion, classification (4 classes: explosion, gunshot, scream, broken glass), localization, and tracking of sound sources, also employing a pan-tilt-zoom (PTZ) camera. Contrary to acti-ve radars, it does not emit any scanning beam but, after receiving environmental sounds, it provides information about the direction of an incoming acoustical signal. Therefore, if a hazardous sound event is detected (i.e. explosion, gunshot, broken glass, scream) the PTZ camera points automatically into the direction of the event.

Description

The device consists of some new kinds of multichannel miniature sound intensity sen-sors, and a set of digital signal processing algorithms. The functionality of the Passive Acoustic Radar enables: sound source visualization in a 3D space, and a precise PTZ ca-mera steering towards the sound source direction. Multiple sound sources can also be detected and localized. Moreover, the implemented beamforming allows ones to obtain an „acoustical focus” on a part of the spatial scene, when the selected sound source ne-eds to be monitored accurately.The proposed device can significantly improve the functionality of traditional surveillan-ce monitoring systems.

Passive Acoustic Radar

Contact: Józef Kotus, PhD / Department of Multimedia Systemsphone: +48 58 347 29 72 / email: [email protected]

Passive Acoustic Radar in action


Passive Anti-Submarine Warfare Towed-Array Sonars

Purpose

The passive anti-submarine warfare (ASW) towed-array sonar systems are designed for detecting and tracking submarines. Installed on frigates which the Polish Navy received from the US, the sonars were previously not operable. The main objective of their moder-nization conducted at the Gdańsk University of Technology was to recreate the functio-nal structure and software using state-of-art technology and to improve their tactical and technical parameters, make them user-friendly, increase reliability and reduce the size of the sub-systems by using modern technology, both in regard to the equipment and software. Today, they are fully operational on Polish Navy MCM ships, meaning that they meet the strict requirements of the highest technology readiness level (TRL 9).

Description

The ASW towed-array sonars are low-frequency, broadband, passive systems designed with a digital microprocessor, in real-time technology. Good angular resolution has been achieved by generating more receiving beams with modern and effective methods of di-gital signal processing. New effective beamforming algorithms for broadband signals, as well as high resolution methods for spectrum estimation were developed to ensure accu-rate measurements of the bearing of incoming acoustic waves. In addition, algorithms were used for automatic tracking of selected targets. To ensure an adequate transmis-sion rate of the data from the towed transducer array, the VDSL (Very High Speed Digital Subscriber Line) transmission technique is used in the towing cable.


Passive ASW towed-array sonar system

Automatic tracking of submarine in the towed-array sonar system


Personalized Healthcare Solutions for Ambient Assisted Living

Contact: Prof. Jerzy Wtorek, PhD, DSc / Department of Biomedical Engineeringphone: +48 58 347 13 84 / email: [email protected]

Purpose

Ubiquitous healthcare systems used as assisted living solutions will not only help to prevent, detect, and monitor health conditions but will also support sick, elderly, and disabled people to live independently. Health personalization and support for older and immobilized people is a very important target for many national and international ini-tiatives.

Description

It is a multimodal, integrated platform for com-munication, training, and monitoring of health status and environmental conditions and thre-ats at home. A very important component of the presented platform, is a central computer station designed to collect and process data in order to evaluate/classify undergoing event alerts. The re-configurable system consists of a few sensor ne-tworks. The basic one is formed by the central sta-tion serving as a master, and prescribed devices equipped with appropriate interfaces. Different categories of sensor are developed to measure: heart pulse, temperature, body composition pa-rameters (weight, fat content, etc.), electric heart activity (ECG), and physical activity (accelerome-ter). Additionally, special sensors/devices can be integrated with the system depending on the type of a chronic illness, e.g. diabetes – glucose concentration, blood hypertension - blood pressu-re, etc. A set of sensors devoted to monitor essen-tial processes or events include, inter alia: instan-taneous water and electrical power consumption, temperature and fire detection, toilet or bath uti-lization, water and gas leakage.


Purpose

Optical Coherence Tomography (OCT) is one of the most powerful optical methods for non-invasive examination of inhomogeneous objects. Our research interests have been focused on OCT with advanced polarization-sensitive analysis (PS-OCT) and with spectro-scopic analysis. It brings unique benefits to OCT measurements, which enable a better characterization of the tested devices and materials. This method is useful, for example in the investigation and quality assessment of complex objects like printed electronic parts or polymer composite materials.

Description

Polarization-Sensitive Optical Coherence Tomography with Spectroscopic Analysis

PS-OCT system

PBS 1, 2 – polarization beamsplitters NPBS 1, 2 – non-polarization beamsplittersPP – dispersion compensation prism P – linear polarization plateQWP 1, 2 – quarter-wave plate

HWP – half-wave plateOH – optical measurement head

PS-OCT measurements examples

Contact: Marcin Strąkowski, PhD / Department of Metrology and Optoelectronicsphone: + 48 58 347 13 61 / email: [email protected]

PS-OCT intensity image of liquid crystal sample; the defected area has been indicated by red contour

PS-OCT tomography image of liquid crystal retar-dation angle


Radio Frequency Trajectory Monitoring

Purpose

The Radio Frequency Trajectory Monitoring system allows to monitor trajectory and com-municate with a launched rocket with the use of radio frequency methods.

Description

The trajectory is estimated by combining different RF signal measurements based on continuous wave communication (transmitter-receiver), supported by inertial sensors. The trajectory calculation is done on the receiving side, which can be both, on-board RFTM terminal (BRT) or ground reference stations (GRS - which sends the measurements to the ground computational station, GCS - where the trajectory is calculated). The tra-jectory estimation results are obtained (by the ground computational station) after the rocket’s landing.


Prototype components of the RFTM system used for test sessions

The research from DEWI project (www.dewi--project.eu) leading to these results has

received funding from the ARTEMIS Joint Undertaking under grant agreement n°

621353 and from the Polish National Centre for Research and Development.


Purpose

Manufacturing of modern thin-film optical and microelectronic devices in a low-pressu-re plasma process requires precision and strict control of the process in order to obtain required properties and good quality of the final product. It stimulates the search for effective diagnostic tools. The aim of this presented optoelectronic system is to monitor in-situ growth of thin films in CVD processes.

Description

Raman Modular System with Fibre-Optic Probes for Remote Monitoring of CVD Processes

Design of Raman system for in-situ monitoring of µPA CVD process: (a) excitation part, (b) acquisition part; 1- coupler, 2 - optical fibre, 3 -excitation probe, 4-6 – objective, 5 – bandpass filter, 7 – window, 8 - growing film, 9 - window, 10-12 - objective, 11 – notch filter, 13 - collecting probe, 14- fibre bundle, 15- adapter; dimensions are given in millimeters.

Contact: Marcin Gnyba, PhD / Department of Metrology and Optoelectronicsphone: +48 58 347 24 82 / email: [email protected]


Purpose

Our biometric system increases the security level of mobile workstations by combining face recognition technology with analysis of the user’s behaviour. Mobile devices often serve as data banks containing confidential information, either personal, corporate or governmental. At the same time the risk of unauthorized access to their resources is much higher than in the case of desktop computers. Therefore, additional biometric protection is necessary.

Description

Our application integrates with Microsoft Windows operating systems and replaces the standard password-based login with an identity verification procedure, performing face identification along with liveness detection. The architecture of the software is modular so that many experimental configurations can be tested within the real-life application. Apart from providing the visual login option, the software monitors a user’s presence and locks the operating system when the computer is left without supervision. Another feature is the possibility to secure access to selected files by means of face recognition.

An additional module of our biometric security system detects anomalies in keystroke pat-terns of a user. As soon as an intruder is detected, the software can lock the workstation immediately or generate a silent alarm, recording the appropriate information in a log file. We are also investigating the possibilities of providing identity verification based on ana-lysis of a user’s habits or patterns discovered in the interaction with graphical interfaces.Our system is fully customizable; thus, we are able to provide the required balance be-tween the supplied security level and the computational complexity of algorithms, which can be adjusted to suit the characteristics of the protected device.

SART-2 – Biometric Security System for Mobile Workstations

Contact: Maciej Smiatacz, PhD / Department of Intelligent Interactive Systemsphone: +48 58 347 26 89 / email: [email protected], http://sart2.eti.pg.gda.pl/


Purpose

SchematicLab is the product of a project which aims at creating a new e-service to enable designing electronic printed circuit boards (PCB). The designer can instantly order the required devices directly from the proposed internet application. In this way, the time from the moment of having a design idea to the mo-ment of producing a prototype is greatly reduced (logistic tasks are performed routinely in the SchematicLab system). Testing and simulation, along with the ability to generate a 3D model of the board, are also supported.

Description

The idea for this project was introduced in response to the current lack of this type of software on the market of web--applications.

The underlying assumption and intent of this project is to develop a solution which re-sembles CAD-type tools, which are well-known and appreciated by designers owing to their intuitive interface.The project is implemented while bearing in mind the large number of hobbyists intere-sted in the construction of electrical devices and circuits. The application also provides the possibility of prompt publication of the newly invented solutions with a common library of components shared by the users.

Contact: Professor Zdzisław Kowalczuk, PhD, DSc, MScEE / email: [email protected] /Department of Decision Systems and Robotics / phone: +48 58 347 2018/2298,Adam Cichosz, MSc / email: [email protected] Wszolek, MSc / email: [email protected]

SchematicLab for Designing Electronic Printed Circuit Boards

Exemplary printed board


Purpose

The sensor network node, equipped with a low-resolution camera, observes the street and detects moving objects. The number, and the speed of the detected objects, are transmitted using a low-power license-free radio transceiver to another neighbouring node. All the nodes create a self-organized network. The prototype sensor network node has been realized in two versions: FPGA and ASIC. The ASIC version consumes approxi-mately 500mW and it can be powered from a photovoltaic solar panel combined with a single cell Li-Po battery.

Description

Sensor network:• low power radio transceivers, ISM license-free band;• low power consumption, low hardware and installation costs;• low maintenance costs;• installation on street lamp-poles;• possibility of autonomous power supply.Each sensor network node consists of:• simple camera sensor;• typical transceiver.Advantages:• traffic analysis;• possibility of interaction with traffic lights;• support for emergency vehicles;• detection and localization of traffic jams;• snow information (pictures from cameras);• information for citizens, radio, internet, street information panels;• monitoring of temperature, noise, intensity of the sunlight;• operation in crisis situations.

Sensor Network for City Traffic Monitoring

Contact: Marek Wójcikowski, PhD / Department of Microelectronic Systemsphone: +48 58 347 19 74 / fax: +48 58 347 23 78 / email: [email protected]


Purpose

Sensor Positioning System is a custom solution that was designed to support identifica-tion of sensors deployed on engines during tests. The system utilizes various methods (RFID, vision, inertial) in order to deliver spatial information about deployed sensors.

Description

Sensor Positioning System (SPS) enables to identify and localize in 3D sensors deployed on the Unit Under Test (UUT). SPS uses radio frequency identification, inertial as well as optical methods to deliver the accurate position of deployed sensors. SPS supports the user during the engine calibration phase by creating a list of deployed sensors, as well in subsequent phases, by delivering information about the precise localization of sen-sors. Each sensor is recognized on the basis of the individual LED broadcasting pattern which is assigned during the engine calibration phase. Information about sensors (list of deployed sensors, position in 3D) is utilized by external software for test management.

Sensor Positioning System


The research from DEWI project (www.dewi--project.eu) leading to these results has

received funding from the ARTEMIS Joint Undertaking under grant agreement n°

621353 and from the Polish National Centre for Research and Development.

First prototype of the localization sensor Localization tests conducted on a real engine

New version of the localization sensor Obtained accuracy results for the localiza-tion of 6 sensors


SMOL – Dedicated Domain Language and Simulation Platform

Purpose

SMOL is a dedicated domain language for the description of features, mechanisms, and networked devices. The semantics of this language enable a precise mapping of the re-lationships existing in real network systems. The principal task of the system designer is then simply to precisely define and program the requirements (both structural and functional) for the designed network system.

Description

The idea of the SMOL project is focused on building a complex platform which allows the designers to describe, using SMOL - the SMO Language, the elements of automation and measurement networks. The SMOL platform not only gives you the opportunity to statically describe the network system, but also to dynamically simulate the operation of the designed system.The simulation module can help the designer with finding the weak points of the ne-twork. In particular, the SMOL system can be used for optimization of the structure of the network by simulating the effects of network overload. The SMOL platform is in con-tinuous and intensive development, and the number of available implemented features is still increasing.

The scope of the undertaken work also em-braces a parser, which allows the translation of codes written in SMOL into a programming language understood by a given computer fra-mework. The environment meant for SMOL allows the user to access two component libra-ries: library for precise mapping of the network structure, and library containing a collection of features of the System for Monitoring Networ-ked Objects referred to as SMO.

Contact: Prof. Zdzisław Kowalczuk, PhD, DSc, MScEE / email: [email protected] of Decision Systems and Robotics / phone: +48 58 347 2018/2298,Jakub Wszolek, MSc / email: [email protected]

Graphical representation of a network


Purpose

The sound processing system was developed as a part of the supercomputer cluster-ba-sed “KASKADA” framework intended to facilitate parallel processing of a multiplicity of audio and video streams received from video cameras. The service running on this plat-form offers the functionality of detecting, classifying, and localizing acoustic events which are symptomatic of threats to the safety of people and property.

Description

The service is executed in the supercomputing platform KASKADA using a client applica-tion, which in turn can run on a PC or mobile platform. The service analyzes live streams from microphones and specialized acoustic sensors. Whenever a threatening event is de-tected (e.g. a gunshot, scream, breaking glass or explosion), the information is passed to the user via the graphical interface or an sms(text) message. The localization of the event is also calculated and is used to point the camera in the direction of the recognized event automatically.

Sound Recognition Service – A Supercomputer Service Able to Detect, Classify and Localize Threatening Acoustic Events

Contact: Adam Korzeniewski, MSc / Department of Multimedia Systemsphone: +48 58 347 23 98 / email: [email protected]


Street Traffic Radar

Purpose

Street Traffic Radar is designed to deliver near real-time information about traffic condi-tions in operational areas.

Description

The subsystem delivers information about traffic congestion, the average speed of vehic-les, lane occupation, etc. Street Traffic Data is a mobile solution based on custom-made devices that utilize various radar methods. Information delivered by STR can be visuali-zed in dedicated GIS tools, and it is available through Web Services in open standard.

Street Traffic Radar mounted on a street pole (left), during a laboratory test (right)

Visualization of the traffic level in Gdańsk based on the Street Traffic Radar and TriStar system

This work has been funded by the Polish Na-

tional Centre for Research and Development

(GA number ARTEMIS-2012-1/8/2013) and by

the Artemis JU (GA number 333020) as part of

the ACCUS project (http://accusproject.eu).



Contact: Józef Kotus, PhD / Department of Multimedia Systemsphone: +48 58 347 29 72 / email: [email protected]

System for Creating Dynamic Maps of Noise Threats Employing Grid Computing

Purpose

Main purpose of the presented design are: providing detailed information about the no-ise threats that occur every day in city areas and the prevention of the noise induced hearing loss especially among young people. An experimental system designed for the continuous monitoring of the acoustic climate of urban areas was developed and imple-mented within the PLGrid Plus project. The assessment of environmental threats is per-formed based on online data, acquired through a grid of engineered monitoring stations and selected psychoacoustical properties of the human hearing system.

Description

Dynamic maps of noise threats, including auditory effects which are caused by exposure to noise, are created and updated on the basis of data obtained from a distributed sen-sors network integrated with the PL-Grid supercomputer infrastructure. Operations are performed employing a dedicated noise prediction model, optimized towards working on a computer cluster. In addition, predicted maps may be adjusted using real noise level measurements. This approach allows for generating more precise maps, but also for veri-fying mathematical source models, utilized in the process. The work presented resulted in services running on a supercomputer grid, ensuring credible noise distribution results in large areas, displayed on digital maps, that can be dynamically updated.


Purpose

The solution is aimed at integrating the spaceborne/airborne, “just captured”, imagery with other types of spatial data in a geographical context. The solution fits any applica-tion where the geo-referencing of the observational data and its nearly real time availa-bility is a crucial aspect.

Description

The main part of the solution are autonomous geo-referencing algorithms which embed the imagery into the geographical context. Algorithms are based on advanced, State of the Art, pattern recognition and computer vision methods.The prototype system involves software and hardware components. The hardware, i.e. platforms and sensors, may be fitted to the user needs. The prototype has been develo-ped, and successfully tested, for different types of imagery and a broad range of spatial resolutions. Particularly, the airborne data was captured from low altitude with the use of a micro UAV platform. The spaceborne imagery was obtained from the polar-orbiting meteorological satellites equipped with the Advanced Very High Resolution Radiometer.

System for Geo-Referencing And Integration of the Spaceborne and Airborne Real Time Imagery

Contact: Krzysztof Bruniecki, PhD / Department of Geoinformaticsphone: +48 58 347 28 85 / email: [email protected]


System for Remote Monitoring of Position of Persons in Indoor Environment – SALON

Purpose

This system was designed as support for public order agencies such as border guards or fire brigades during interventions in unknown buildings or enclosed spaces where the knowledge of officers’ position may improve the safety of their work.

Description

This indoor positioning system has been significantly improved in the course of several years of development. SALON is made up of three types of devices:• personal identification modules (PIM), which are carried by monitored persons,• reference nodes (RN) which are installed in an ad-hoc manner around the area of

operation,• server, responsible for data collection, calculation of officer’s positions and their pre-

sentation on 3D maps of buildings.In order to obtain the highest precision of the positioning service in various environ-ments, the position estimation in PIM modules is based on inertial navigation (INS) with the addition of:• detection of steps and cancellation of the position drift caused by noise from MEMS

accelerometers using the zero-velocity update algorithm (ZUPT);• measurements of the geomagnetic field to reduce drift of attitude data from MEMS

gyroscopes;• measurements of air pressure for altitude change tracking;• optional measurements of distances between nodes, performed by UWB modules

working in 6 GHz band.In addition to position estimation, SALON devices may be used to inform the system su-pervisor that some dangerous events (e.g. free fall, gun fire) were detected near monito-red persons.

Contact: Jarosław Sadowski, PhD / Department of Radiocommunication Systems and Networksphone: +48 58 347 17 73 / email: [email protected]


Purpose

Children with special education needs (SEN) represent a large group of pupils (about 4%). Many of these children are not able to understand speech being articulated too fast for them. The engineered system allows for a time scale modification (TSM) of speech signals (i.e. time-expansion) in real-time. As a result, the child could participate in classes with normal-hearing children.

Description

The system consists of two main parts: the speech-stretching device, and the worksta-tion for performing adequate hearing examination. At the beginning, every pupil has to perform a series of hearing tests (the examination is supervised by the specialist) em-ploying a PC software application. The designed mobile device stretches the speech si-gnal in real-time. It was necessary to design methods allowing the performance of this operation, and to ensure as small as possible the difference in the duration of the input (original speech) and the output (stretched signal). Additionally, dependent on the rate of the input speech, time scale factors are adapted in such a way that fast spoken speech is stretched up more than slow speech.

System Supporting Speech Perception for Special Educational Needs of Schoolchildren

Contact: Piotr Odya, PhDDepartment of Multimedia Systems phone: +48 58 347 23 01 / fax: +48 58 347 11 14 email: [email protected]


The Interactive Eyeglasses for Mobile, Perceptual Computing

Purpose

Development of an open platform in the form of multisensory electronic glasses and on the integration and designing of new intelligent interaction methods using the eGlasses eyewear platform.

Description

The activity is concentrated on long-term research and technological innovation in per-ceptual and super-perceptual (e.g. heart rate, temperature) computing. It is an emerging technology that is also focused on the creation of mobile, perceptual media. Perceptual media refers to multimedia devices with added perceptual user interface capabilities. These devices integrate human-like perceptual awareness of the environment, with the ability to respond appropriately. This can be achieved by using automatic perception of an object’s properties and delivering information about the object’s status as a result of reasoning operations. For example, using the eGlasses, it will be possible to control a device that is recognized within the field of view using the interactive menu. Other exam-ples include presentation of a recognized person name, recognition of people with abnor-mal physiological parameters, protection against possible head injuries, etc. The platform will use currently available user-interaction methods, new methods deve-loped in the framework of this research (e.g. a haptic interface) and will enable further extensions to introduce next generation user-interaction algorithms, e,g. used in intelli-gent user interactions, particularly useful for healthcare professionals and people with disabilities or at risk of exclusion.

Contact: Jacek Rumiński, PhD / Department of Biomedical Engineeringphone: +48 58 347 26 78 / email: [email protected]


Purpose

The system was developed as a part of the supercomputer cluster-based “KASKADA” fra-mework, intended to facilitate the parallel processing of a multiplicity of audio and video streams received from video cameras. The system provides an application for smart su-rveillance backed up by the supercomputing cluster’s computational power. Its objective is to realize unattended monitoring of urban spaces using a distributed camera infra-structure and advanced video analysis. The system is focused on balancing both privacy and safety in public areas.

Description

The system was developed using multilayer architecture. In the first layer algorithms are installed, being integrated in the second layer as simple services; subsequently, several simple services are connected in the workflow creating a complex service. A user is allo-wed to design specific processing scenarios employing implemented algorithms. Instead of video stream transmission, the system generates alerts whenever dangerous events occur. Algorithms developed especially for this system realize object detection, object classifying, people counting, sensitive region detection, congestion, border crossing, re-stricted area intrusion. The video streams are anonymized, the anonymization algorithm encrypts reversibly the visual content.

Video Event Recognition System with Enhanced Privacy Protection

Contact: Andrzej Ciarkowski, MSc / Department of Multimedia Systems phone: +48 58 347 16 36 / email: [email protected]


Purpose

The Virtual Whiteboard is a computer application allowing emulation of an electronic whiteboard using a multimedia projector, a screen, a computer and a simple camera con-nected to a computer’s USB port.

Description

The multimedia projector is fixed under the ceiling. A camera can be directly attached to the multimedia projector or placed on a stand at an appropriate distance from the screen, so that it fits in the video frame. The user is situated between the projector and the screen. An application installed on the computer manages the aforementioned com-ponents and recognizes dynamic hand gestures, i.e. constituted by motion trajectories, and static gestures, i.e. palm shapes. Apart from the basic functionality of the whitebo-ard, which is content entering, the system enables the user to interact with objects, e.g. rotation, zooming in/out, cropping and shifting are possible. A course of events during the work with the system can be saved and recreated, preserving time dependencies. The Virtual Whiteboard works with multimedia presentation browsers, providing functiona-lity to browse slides and add notes.

Virtual Whiteboard

Contact: Piotr Odya, PhDDepartment of Multimedia Systemsphone: +48 58 347 23 01 / fax: +48 58 347 11 14 email: [email protected]


Versatile Real Time Vector Based Electronic Map Update System for Mobile Devices

Fig. a) The system architecture and b) The front view of the vector map updating system with the vector layer ready to update

Contact: Jerzy Demkowicz, PhD / Department of Geoinformatics phone: +48 58 347 25 95 / email: [email protected]

Purpose

This is a versatile system dedicated for chart database updating from mobile devices that can be run on almost any platform, for instance on a vehicle fleet management systems where highly interactive approach is required. The system is small, easy to maintain and cheap.

Description

This is the first such a system for small, mobile devices available and at the same time it is the answer for the near real time vector map updating requirements. The typical chart database for the world exceeds terabytes (TB) in size and the spatial data management and dissemination is quite challenging. The Electronic Map Update System is addressed to mobile users allowing simultaneous updating and correcting maps from any place. The mobile part is founded on static and dynamic layer vector map concept. The only mobile or desktop device requirement is a web browser. The system has already been successful-ly deployed in a company managing a fleet of some 200 trucks.

a) b)


VisRobot – 3D Mapping with Variable Stereo Baseline

Purpose

The main task of the perspective autonomous vision system (VisRobot) is to explore an unknown environment in a manner similar to the sense of sight. The human vision sys-tem allows us to recognize static and mobile objects as well as to perceive relationships between them. Similarly, our system is designed for 3D mapping using various stereo baselines. We expect to obtain enhanced resolution of the image depth, especially for distant objects. The VisRobot system can be the basis for further object recognition in-spired by the human vision system.

Description

The VisRobot system is a system for 3D mapping with the use of operation of mobile robots which support explora-tion of an indoor static environment. VisRobot helps acqu-iring stereo images, calculating the depth in the images, and constructing a 3D map from the results. Compared to laser rangefinders and structured light systems, our solu-tion is capable of passively measuring the distance of ob-jects in its near and distant vicinity. The length of each baseline is computed by currently con-trolling the actual location and angular pose of the robotic carrier of a camera. Location and pose are obtained using IMU and a mathematical model of the mobile robot. Measu-rement errors bring about inaccuracies in depth. Therefore, we propose an innovative procedure which suitably combi-nes the depth maps gained with variable baselines. The VisRobot system is also provided with a visualization module which presents an effective combined 3D map, as well as a stereo image suitable to a human operator of the system. As the stereo images obtained at large baseline result in excessively large disparities, all such incorrectly interpreted areas are obscured (masked) for the operator.

Contact: Prof. Zdzisław Kowalczuk, PhD, DSc, MScEE / email: [email protected] of Decision Systems and Robotics / phone: +48 58 347 2018/2298Tomasz Merta, MSc / email: [email protected]


Purpose

This product is a prototype version of a mobile application supporting independent mo-vement of the blind. Its objective is to improve the quality of life of visually impaired people, providing them with navigationalassistance in urban areas.

Description

The mobile application is installed on Android smartphones. Voice recognition, speech synthesis and touch screen enhancements are used as the main user interface methods. The spatial data for the system is collected by trained operators and volunteers. They are stored in a central, remote database in a dedicated format, created to fulfill blind people’s requirements. Movement support is achieved with the use of implemented po-sitioning, navigational and guiding algorithms.

Voice Maps – System Supporting Independent Movement of the Blind

Contact: Prof. Andrzej Stepnowski / Head of the “Voice Maps” Consortiumphone: +48 58 347 25 25 / email: [email protected]


Purpose

Today’s digital restoration and archiving solutions have the following serious limitations: - user needs to have access to the licensed software, - process of sound restoration usually requires a time-demanding procedure, - effective sound restoration needs knowledge, experience and skills from the operator.This system is a web-based audio restoration application which enables ones to auto-matically explore digital sound libraries faster, restore more easily, and to preserve their content more efficiently.

Description

The proposed solution has the following features: • no special sound software is needed, • both versions of the signal are archived: original and restored,• restoration could be performed in two modes:

– fully automatic noise and distortion reduction – semi-automatic mode of operation

• no skills from the user are needed in the fully automatic mode, • limited knowledge of digital signal processing is needed in the semi-automatic

mode.The system is dedicated to the removal of typical distortions in music archival recordings, such as:• noise, • impulsive distortions (clicking, based on based on non-linear neural predictor),• parasitic frequency modulation (the “wow” distortion), • signal clipping.

YouArchive.net – Web-Based Audio Restoration System (Online Sound Restoration System for Digital Library Applications)

Contact: Prof. Bożena Kostek / Audio Acoustics Laboratory phone: +48 58 347 27 17 / email: [email protected]

www.youarchive.net

Reconstructed signal

Original signal


Purpose

The system provides various information that allow the making of decisions for urban environments based on current or predicted weather conditions.

Description

WeatherSense is a technolo-gy platform that generates and provides high-resolution weather prediction data inc-luding various weather para-meters such as temperature, humidity, wind, precipita-tion and others. The WeatherSense Web por-tal is also integrated with mobile applications desi-gned to serve operational weather predictions to di-stributed users. Mobile devi-ces deliver tools for weather information display. Currently, three simultane-ous technologies are being developed:• Android application,• Windows Phone 7,• iPhone.The utilized numerical model, namely WRF (Weather Research and Forecast), is originally developed by the National Center for Atmospheric Research (NCAR), the Advanced Re-search WRF (ARW), and the National Center for Environmental Predictions (NCEP). It is run operationally (a 48-hour real-time forecast generated 4 times per day) on the Depart-ment of Geoinformatics’ computer cluster. Predictions and weather data generated by the system are available at http://weathersense.pl

WeatherSense – Numerical Weather Prediction for Poland

Contact: Andrzej Chybicki, PhD / Department of Geoinformaticsphone: +48 58 347 13 26 / email: [email protected]


Purpose

• prototyping and implementation of hardware accelerated algorithms for HD video and audio compression,

• prototyping and implementation of machine vision systems,• prototyping and implementation of parallel data processing systems.

Description

The presented wireless surveillance system module has been used for development of har-dware acceleration for the H.264 video compression standard. In the Xilinx XC6VLX365T FPGA a Microblaze processor with PLB and common memory interface for accelerator mo-dules has been implemented. Linux has been chosen as the operating system for the bo-ard. H.264 encoder software has been installed and modified for hardware acceleration. Hardware acceleration has been achieved for: integer transform, inverse integer trans-form, Hadamard transform, quantization, dequantization, intra-prediction, inter-predic-tion and CAVLC. ASIC version of the H.264 accelerator (technology 90nm) has also been designed. It can be easily integrated with the development board using the expansion sockets.

Wireless Surveillance System Module

Contact: Miron Kłosowski, PhD / Department of Microelectronic Systemsphone: +48 58 347 18 64 / email: [email protected]


Immersive 3D Visualization Lab. The rotary transparent sphere


The computer laboratories

The interior of an Anechoic Chamber used for antenna measurements

Motion Capture System as used in the Laboratory of Advanced Computer Animations


New general purpose computer laboratory opened in 2012 used for mobile applications development


The laboratory of industrial robots in the old building

New general purpose compu-ter laboratory opened in 2012 used for mobile applications development

Computer Networks Laboratory in the old building

The Clean-room Laboratory of Innovative Materials and Devices with the microwave Plasma CVD System used for growth of high quality dia-mond films for microelectronic and electrochemical sensors

The Laboratory of industrial robots

Gdańsk University of TechnologyFaculty of Electronics, Telecommunications and Informatics

Narutowicza 11/12, 80-233 Gdańsk, Polandwww.eti.pg.edu.pl

the innovative faculty - wydział elektroniki, … the innovative faculty for innovative...

Documents