Test Intersection: Status, Results, Preparation for State Data Collection

Test Intersection: Status, Results, Preparation for State Data Collection

Lee AlexanderPi-Ming Cheng Alec GorjestaniArvind Menon

Craig ShankwitzIntelligent Vehicles LabUniversity of Minnesota

Presentation

System Overview Test Intersection Status

Construction Sensing Data collection Analysis

Examples of Data Collected Animations Video

Database status Installation in partner states

Design Documents Cost

System Overview

Mainline surveillance Radar based sensing Provides position, speed, lane assignment, and time to

intersection of each sensed vehicle Minor Road Surveillance

Laser based system provides “profile” of stopped vehicle Used for data analysis, timing of warnings (when DII deployed)

Crossroads Surveillance Used to capture driver behavior (one step or two) NOT part of deployed IDS system

Computation Acquires driver behavior data now Compute warning timing when IDS deployed

Central Processor

Wired/WirelessCommunication



DII

Vehicle waiting toenter traffic stream

Vehicle/DriverClassification

System

Weather/RoadCondition Sensor

DII

Vehicle waiting toenter traffic stream


Transceiver





Radar SensorsBoth Directions of Major Road

(400 ft. range per sensor5 sensors per leg typical

Construction - Mainline

Construction - Mainline

Construction- Vehicle Classification

Construction – Crossroads Surveillance

Construction- Control Cabinet

Test Intersection Status

Mainline surveillance Construction Complete All sensors operational Series of Validation Experiments Complete

Mainline System Performance Results

Detection Rate: 99.990% (5 “misses” out of 51,942) Miss defined as vehicle not

within 40 meters of test zone Results for a single sensor;

multiple sensors decrease likelihood of a “miss”

Camera

Radar

Retro-reflectiveLaser


Lane Data Accuracy Longitudinal Accuracy 8 meters Lane assignment accuracy 90%

• Ambiguity during lane changes, hanging near center line

• Limitations of angular resolution of radar Speed accurate to 1 MPH

ID 144 ID 225

DGPS-ProbeVehicle

ID 169


Vehicle Shadowing

X

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

Vehicle Classification Validation Configuration

DGPS

HorizontalLaser

Vertical Laser

VehicleClassifying

RadarLaserPresenceDetector

Camera

Vehicle Classification Performance

Accuracy approximately 85% based on vehicle height One sensor reduces cost substantially

Grouping conservative….classify as larger than actual

Vehicle Classification: Height Only

CarsLt. Truck

SUV

Med.Truck

Semi.Truck

Crossroads Surveillance

Positions based on locating front of vehicle Working definition of gap Accuracy 1-2 meters Larger concern 1 step or 2, time in crossroads

Performance Left turns sensed, captured correctly 95% of time Right turns sensed, captured correctly 95% of time

Open Issue Straight through captured only 60% right now Camera issues

• Absolute vs. Relative thresholds (being tested today/tonight)• IR Illuminators

Cheaper ($2k system vs. $26K system) We control illumination

Crossroads Trajectory Tracker Validation: Day with Visible Light

Camera

Crossroads Trajectory Tracker Validation: Night with IR Camera

Crossroads Trajectory Tracker Validation: Night with IR Camera

Intersection Surveillance System:Visualization of all Data

Data Collection: Visualization

iDAQ

TrackerSensor

Collector

Removable Hard Drive

TrackedTargets

DataGap Data

RawSensorData

SensorStatusData

Database"friendly" ASCII

files

Collects datafrom all

intersectionsensors

Kalman filterbased trackingof all vehiclesin intersection

Intersection DataAcquisition

System

Hard driveremoved everytwo weeks andtake by courrierto the Intelligent

Vehicles Lab

Data Acquisition – Control Cabinet

Removable Hard Drive

Tracked

Targets

Table

Gap

Data

Table

Raw

Sensor

Table

Sensor

Status

Table

Hwy 52Database

ARWIS

Weather

Table

Batch program copies datafrom removable hard driveand inserts into database

stored on Terrabyte server

Data Acquisition – IV Lab Data Flow/Archival

Batch program finds vehicles enteringintersection from minor road (Vehicles ofInterest (VOI) ) and consolidates tracking

information to new table

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.

Data Acquisition – IV Lab Analysis Processes

Tracked

Targets

Table

Gap

Data

Table

Raw

Sensor

Table

Sensor

Status

Table

Hwy 52Database

ARWIS

Weather

Table

VOI

Intermetiary

Results

Table

Selected

Gaps

Table

Results File

GUI program takes user input of desireddata, queries the database and creates

table of gaps selected by drivers on minorroad. Produces file with compiled results.

QueryProgram

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

Data Acquisition and Analysis

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

Automated queries (can be run as frequently as desired).

Gaps as a function of vehicle classification Gaps as a function of time of day Gaps for Right, Straight, Left turns Percentages of one step vs. two step

maneuver Identification of near misses/accidents Other queries supported as well.

Add license plate reader, further refine data set.

Data Analysis – cont’d

Weird Observational Data For every 100 Right turns,

• 100 Straight-throughs• 5 left turns

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

Can we build one for you?

FLASHBACK!Intersection Build Details from AP 2004

•Radar Stations •Vehicle Classification Stations•Vision Systems•Central Cabinet•Ethernet and Video Cable

$191,837

Cost Data

Electrical Contractor: $101K Bought guys lunch last week in Cannon Falls, must be happy Rethinking Laser for Vehicle Classification Two Crash repairs:

• #1, $2500

• #2, $800

MN vs. Partner States Cost

Minnesota Radar Subsystem: $50K Video (Xroads): $70K Minor Roads: $48K Cabling (Power and Data):

$10k

Grand total (Contractor + HW): $314K

Partner States Radar Subsystem: $50K Video (Xroads): $35K

• 2 masts, not 4• SDRC with IR Illumination,

not IR Cam. Minor Roads: $35K (2 lasers,

not 4) Cabling (Power and Data):

$10k Computer Assy, parts

procurement: $20K Estimated total

(Contractor+HW): $275K

Build one for you?

Final Reports due 28 Feb 2005 Master Design Document will be appendix Can make available to states who wish to

review/help them make decision to install equipment.