3d indoor positioning system final presentation sd may 11-17

31
3D Indoor Positioning System Final Presentation SD May 11-17 Members: Nicholas Allendorf - CprE Christopher Daly – CprE Daniel Guilliams – CprE Andrew Joseph – EE Adam Schuster – CprE Faculty Advisor: Dr. Daji Qiao Client: Dr. Stephen Gilbert Virtual Reality Application Center

Upload: kevork

Post on 12-Feb-2016

61 views

Category:

Documents


1 download

DESCRIPTION

3D Indoor Positioning System Final Presentation SD May 11-17. Faculty Advisor: Dr. Daji Qiao. Members: Nicholas Allendorf - CprE Christopher Daly – CprE Daniel Guilliams – CprE Andrew Joseph – EE Adam Schuster – CprE. Client: Dr. Stephen Gilbert Virtual Reality Application Center. - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: 3D Indoor Positioning System Final Presentation SD May 11-17

3D Indoor Positioning SystemFinal PresentationSD May 11-17

Members:Nicholas Allendorf - CprE

Christopher Daly – CprEDaniel Guilliams – CprE

Andrew Joseph – EEAdam Schuster – CprE

Faculty Advisor:Dr. Daji Qiao

Client: Dr. Stephen GilbertVirtual Reality Application Center

Page 2: 3D Indoor Positioning System Final Presentation SD May 11-17

2

• Currently, there is no inexpensive system that is able to accurately localize and track fingertips – Small scale (cm level) vs. larger scale (m level) accuracy

• Such a system could be used as an input device or controller for human-computer interaction– It could be used for virtual reality systems, touch tables,

or a “Minority Report”-style user interface

Problem Statement

Slide of 31

Page 3: 3D Indoor Positioning System Final Presentation SD May 11-17

3

• Create a system capable of accurately tracking fingertips in three dimensions

• Incorporate the ability to support many users simultaneously

• Design the system so that it is easily reproducible

Project Goal

Slide of 31

Page 4: 3D Indoor Positioning System Final Presentation SD May 11-17

4

Functional Requirements• Provide a 3D position of all tracked fingertips

within a 2m x 2m x 2m indoor region with 1 centimeter accuracy

• Update positions 15 times per second (15 Hz)• The system shall be capable of tracking as many

as 60 object positions simultaneously• Positions shall be displayed in a graphical

interface so the position may be viewed in real time

Slide of 31

Page 5: 3D Indoor Positioning System Final Presentation SD May 11-17

5

Non-Functional Requirements• The device used by the potential user shall be

small, lightweight and durable• The device shall be able to go three weeks

without requiring any sort of recharging• The tracking infrastructure surrounding shall be

easy to set up so the tracking system may be moved to different locations when required

• The system shall be reproducible with consistent quality

Slide of 31

Page 6: 3D Indoor Positioning System Final Presentation SD May 11-17

6

• Small device size limits choice of technology

• Need for battery life forces much of the work to be done by the infrastructure

• Want the system to be as non-intrusive as possible

• Some part of the device must be uniquely identifiable to software

Constraints

Slide of 31

Page 7: 3D Indoor Positioning System Final Presentation SD May 11-17

7

Market Survey• There are several systems available that perform

gesture/pose recognition, but not localization

• Several systems that provide localization, but are not wireless, do not track finger movement, require holding a device, etc.– Playstation Move/Nintendo Wii

• Our project in unique in that it will be wireless with accurate absolute fingertip localization and no hand held device

Slide of 31

Page 8: 3D Indoor Positioning System Final Presentation SD May 11-17

8

Considered TechnologiesTechnology Advantages Disadvantages

Ultrasonic Crickets

Existing systems available

Low accuracy, latency issues, bulky devices

RSS/ Range Free Scalable Low accuracy, complex custom hardware required

Accelerometer/ Gyroscopic

Low cost, potentially highly accurate

Relative motion only, calibration required each use

Mini-GPS High accuracy, scalable Interference prone, very high time resolution required

Optical High accuracy Occlusion issues, device identification

Slide of 31

Page 9: 3D Indoor Positioning System Final Presentation SD May 11-17

9

Range and Accuracy of Current Positioning TechnologiesSource: IPIN Website

http://www.geometh.ethz.ch/ipin/index/IPIN_Opening_Session.pdf

Slide of 31

Page 10: 3D Indoor Positioning System Final Presentation SD May 11-17

10

Choice of Technology• Optical/Infrared tracking

– Most practical solution– Accuracy is a function of camera resolution– No need to develop custom hardware– Existing IR tracking systems are highly accurate, but

very expensive ( $5,000 + )– Our system will cost less than $1000

• Plan of Attack– Use stereo pairs of cameras to determine location of IR

LEDs on fingertips.

Slide of 31

Page 11: 3D Indoor Positioning System Final Presentation SD May 11-17

11

System Components• Glove

– Contains IR LEDs and colored cloth on fingertips which are tracked by the cameras and software

• Infrastructure– Provides mounting points for the cameras

• Cameras– Mounted in stereo pairs around periphery of

infrastructure– Detect IR LEDs and pass images to server for processing

• Server/Computer– Performs image processing, calculates position, and runs

the GUI

Slide of 31

Page 12: 3D Indoor Positioning System Final Presentation SD May 11-17

12

System Block Diagram

Slide of 31

Page 13: 3D Indoor Positioning System Final Presentation SD May 11-17

13

Hardware Platforms• Cameras : Logitech QuickCam Pro 9000

– Varying resolution, as high as 1280 x 720 @ 15 fps– 75 degree field-of-view– USB 2.0

• Computer : Dell XPS– Dual Core Intel Processor @ 2.93 GHz (4 Virt. Cores)– 4 GB RAM

• Gloves/LEDs : 890 nm Low Profile Infrared LEDs

• Infrastructure : 8020 Aluminum Framing

Slide of 31

Page 14: 3D Indoor Positioning System Final Presentation SD May 11-17

14

Software Platforms• Computer Operating System : Windows 7

• Image Processing/Stereo Calibration : OpenCV

• Graphical User Interface : OpenGL

• Development Environment: Visual Studio 2008

Slide of 31

Page 15: 3D Indoor Positioning System Final Presentation SD May 11-17

15

Cost BreakdownComponent Cost/Per Total Cost

Cameras $50.00 $400

Filter Materials $7.50 $30

IR LED/Glove Parts - $165Infrastructure Materials - $108

Computer Provided Provided

Work Hours $20.00 $48,000

TOTAL $48,703

Slide of 31

Page 16: 3D Indoor Positioning System Final Presentation SD May 11-17

16

System Detail: Gloves• 2 IR LEDs per fingertip – one front and one back• Uniquely colored fabric on each finger for ID• Battery pack and wiring to connect the LEDs to

the battery and power switch

Slide of 31

Page 17: 3D Indoor Positioning System Final Presentation SD May 11-17

17

• Provide a stable platform to mount the cameras

• Allows for flexibility in camera mounting position and orientation

• Made from 80/20 aluminum framing

System Detail: Infrastructure

Slide of 31

Page 18: 3D Indoor Positioning System Final Presentation SD May 11-17

18

System Detail: IR Cameras• Stereo pairs of cameras resolve 3D position of

LEDs• One Camera of each pair has an IR filter to block

visible light• Cameras mounted so that pairs’ field of view is

intersecting as large of an area as possible• Attached to infrastructure with articulating

mounts to allow for flexible positioning

Slide of 31

Filter

Page 19: 3D Indoor Positioning System Final Presentation SD May 11-17

19

IR Filter Response to Light

Slide of 31

IR LEDs: 890 nm Wavelength

Page 20: 3D Indoor Positioning System Final Presentation SD May 11-17

20

Graphical User Interface

Slide of 31

• Simple 3D position viewer• Used for testing to show

how the system is working• Displays color and position

of recognized fingertips• Incorporates camera feeds

to show location of recognized points

Page 21: 3D Indoor Positioning System Final Presentation SD May 11-17

21

Camera Calibration• Camera lenses introduce distortion in the images,

particularly around the edges of the images

• In order to get accurate localization, each stereo pair of cameras must have parallel viewing rays– OpenCV has a calibration routine which introduces error

correction to compensate for this

• Once calibrated, cameras do not need calibration unless they are moved relative to each other or the infrastructure

Slide of 31

Page 22: 3D Indoor Positioning System Final Presentation SD May 11-17

22

Localization Process

Slide of 31

Page 23: 3D Indoor Positioning System Final Presentation SD May 11-17

23

Testing Results• The system is functional, but not to the level set

forth by the project requirements.• Several limitations have been encountered with

the design:– USB 2.0 bandwidth is not large enough for 8 cameras,

even with reduced resolution – Positioning accuracy is poor, positioning precision is

good – Image processing is too intensive to maintain 15 fps,

even with only two cameras

Slide of 31

Page 24: 3D Indoor Positioning System Final Presentation SD May 11-17

24

Testing Results: Calibration• Accurate calibration is very difficult

– Average calibration has an average error of 0.8 px– Our best: 0.415 px– 0.1 is a good target

Slide of 31

5 10 15 20 25 30 35 40 45 50 55 60 65 70 75 80 85 90 95 1000

0.10.20.30.40.50.60.70.80.9

Average Error (pixels)

Average Error (pixels)

# of Frames used in Calibration

Page 25: 3D Indoor Positioning System Final Presentation SD May 11-17

25

Testing Results: Localization• Localization accuracy varies greatly

Slide of 31

0 50 100 150 200 250 300

-50

-40

-30

-20

-10

0

10

20Discrepency in Measured vs. Actual ditsance (cm)

Discrepency (cm)

Actual Distance from Camera (cm)

Diff

eren

ce in

mea

sure

d vs

. act

ual d

istan

ce (c

m)

Page 26: 3D Indoor Positioning System Final Presentation SD May 11-17

26

Testing Results: USB Cameras• USB 2.0 bandwidth is 480 Mbps

– One camera @ 30 fps uses ~48% of that!– Bandwidth limited to two cameras – With reduced resolution, accuracy suffers even more– PCI USB card grants one extra camera

Slide of 31

Resolution FPS Bandwidth Used

(PCI Card)

Bandwidth Used

(Built-in USB)

640x480 30 67% 48%320x240 30 18% 16%

Page 27: 3D Indoor Positioning System Final Presentation SD May 11-17

27

Testing Results: Durability• Gloves:

– Battery life tested at 16 hrs continuous usage before the system has trouble picking up LEDs at distance

– Initially, battery packs had problems slipping out and connections coming un-soldered

– Problems have been resolved, and the glove functions very well

Slide of 31

Beginning of test After 16 hrs continuous use

Page 28: 3D Indoor Positioning System Final Presentation SD May 11-17

28

Final Results• The design of our system is feasible but still

needs to be improved in several areas– Accuracy/Calibration need work– USB bandwidth issues to be resolved– IR LED location and color recognition algorithms must be

sped up if 8 cameras are going to be used• Ultimately, we ran out of time

– Should have looked in to system limitations earlier– Took too much time to learn how to manipulate OpenCV

to our needs– Lack of foresight had us scrambling to find questionable

solutions to major issues

Slide of 31

Page 29: 3D Indoor Positioning System Final Presentation SD May 11-17

29

Team Member Duties• Daniel Guilliams - CprE

– Team leader, client communication, 3D localization, GUI

• Andrew Joseph – EE– Weekly status reports & other documentation, glove design and

implementation,

• Nicholas Allendorf – CprE– IR marker detection, color recognition, general image processing guru

• Chris Daly - CprE– Camera control, IR filters, synchronous image capture

• Adam Schuster - CprE– Infrastructure, camera calibration, camera pair design and assembly

Slide of 31

Page 30: 3D Indoor Positioning System Final Presentation SD May 11-17

30

Questions?

Slide of 31

Page 31: 3D Indoor Positioning System Final Presentation SD May 11-17

31

Thanks for your time!

Slide of 31