Presentation is loading. Please wait.

Presentation is loading. Please wait.

Test Intersection: Status, Results, Preparation for State Data Collection Lee Alexander Pi-Ming Cheng Alec Gorjestani Arvind Menon Craig Shankwitz Intelligent.

Similar presentations


Presentation on theme: "Test Intersection: Status, Results, Preparation for State Data Collection Lee Alexander Pi-Ming Cheng Alec Gorjestani Arvind Menon Craig Shankwitz Intelligent."— Presentation transcript:

1 Test Intersection: Status, Results, Preparation for State Data Collection Lee Alexander Pi-Ming Cheng Alec Gorjestani Arvind Menon Craig Shankwitz Intelligent Vehicles Lab University of Minnesota

2 Presentation u System Overview u Test Intersection Status v Construction v Sensing v Data collection v Analysis u Examples of Data Collected v Animations v Video u Database status u Installation in partner states v Design Documents v Cost

3 System Overview u Mainline surveillance v Radar based sensing v Provides position, speed, lane assignment, and time to intersection of each sensed vehicle u Minor Road Surveillance v Laser based system provides “profile” of stopped vehicle v Used for data analysis, timing of warnings (when DII deployed) u Crossroads Surveillance v Used to capture driver behavior (one step or two) v NOT part of deployed IDS system u Computation v Acquires driver behavior data now v Compute warning timing when IDS deployed

4

5 Construction - Mainline

6

7 Construction- Vehicle Classification

8 Construction – Crossroads Surveillance

9 Construction- Control Cabinet

10 Test Intersection Status u Mainline surveillance v Construction Complete v All sensors operational v Series of Validation Experiments Complete

11 Mainline System Performance Results u Detection Rate: 99.990% (5 “misses” out of 51,942) v Miss defined as vehicle not within 40 meters of test zone v Results for a single sensor; multiple sensors decrease likelihood of a “miss”

12 Mainline System Performance Results u Lane Data Accuracy v Longitudinal Accuracy 8 meters v Lane assignment accuracy 90% Ambiguity during lane changes, hanging near center line Limitations of angular resolution of radar v Speed accurate to 1 MPH

13 Mainline System Performance Results u Vehicle Shadowing Performance: Range accuracy will be no worse than 75 feet if lateral shadowing occurs Performance: Can resolve 2 vehicles if separated by 50 or more feet

14 Vehicle Classification Validation Configuration DGPS Horizontal Laser Vertical Laser Vehicle Classifying Radar Laser Presence Detector Camera

15 Vehicle Classification Performance u Accuracy approximately 85% based on vehicle height v One sensor reduces cost substantially u Grouping conservative….classify as larger than actual

16 Vehicle Classification: Height Only Cars Lt. Truck SUV Med. Truck Semi. Truck

17 Crossroads Surveillance u Positions based on locating front of vehicle v Working definition of gap v Accuracy 1-2 meters v Larger concern 1 step or 2, time in crossroads u Performance v Left turns sensed, captured correctly 95% of time v Right turns sensed, captured correctly 95% of time u Open Issue v Straight through captured only 60% right now v Camera issues Absolute vs. Relative thresholds (being tested today/tonight) IR Illuminators  Cheaper ($2k system vs. $26K system)  We control illumination

18 Crossroads Trajectory Tracker Validation: Day with Visible Light Camera

19 Crossroads Trajectory Tracker Validation: Night with IR Camera

20

21 Intersection Surveillance System: Visualization of all Data

22 Data Collection: Visualization

23 Data Acquisition – Control Cabinet

24 Data Acquisition – IV Lab Data Flow/Archival 120 Gbyte IDE Drive requires replacement once every 2 weeks. DOT will have to dispatch someone to swap out to mail to U of MN.

25 Data Acquisition – IV Lab Analysis Processes Batch program finds vehicles entering intersection from minor road (Vehicles of Interest (VOI) ) and consolidates tracking information to new table User specified queries User specified results

26 Data Acquisition and Analysis u Database system has been design u Initial automated queries have been completed. u Will be validating results next two weeks u Automated and specialized queries supported

27 Automated queries (can be run as frequently as desired). u Gaps as a function of vehicle classification u Gaps as a function of time of day u Gaps for Right, Straight, Left turns u Percentages of one step vs. two step maneuver u Identification of near misses/accidents u Other queries supported as well. v Add license plate reader, further refine data set.

28 Data Analysis – cont’d u Weird Observational Data v For every 100 Right turns, 100 Straight-throughs 5 left turns v 2 drivers have missed intersection approaching from west, none have missed from right Both crashes, damages could have been much worse. Last crash, no sensor damage, just mount damage

29 Can we build one for you?

30 FLASHBACK! Intersection Build Details from AP 2004 Radar Stations Vehicle Classification Stations Vision Systems Central Cabinet Ethernet and Video Cable $191,837

31 Cost Data u Electrical Contractor: $101K v Bought guys lunch last week in Cannon Falls, must be happy v Rethinking Laser for Vehicle Classification v Two Crash repairs: #1, $2500 #2, $800

32 MN vs. Partner States Cost u Minnesota v Radar Subsystem: $50K v Video (Xroads): $70K v Minor Roads: $48K v Cabling (Power and Data): $10k u Grand total (Contractor + HW): $314K u Partner States v Radar Subsystem: $50K v Video (Xroads): $35K 2 masts, not 4 SDRC with IR Illumination, not IR Cam. v Minor Roads: $35K (2 lasers, not 4) v Cabling (Power and Data): $10k v Computer Assy, parts procurement: $20K u Estimated total (Contractor+HW): $275K

33 Build one for you? u Final Reports due 28 Feb 2005 u Master Design Document will be appendix u Can make available to states who wish to review/help them make decision to install equipment.


Download ppt "Test Intersection: Status, Results, Preparation for State Data Collection Lee Alexander Pi-Ming Cheng Alec Gorjestani Arvind Menon Craig Shankwitz Intelligent."

Similar presentations


Ads by Google