A Tracking-based Traffic Performance measurement System for

Roundabouts/Intersections

PI: Hua Tang

Graduate students: Hai Dinh

Electrical and Computer Engineering Department

University of Minnesota Duluth

Proposed FY11 project

• The goal is to develop a tracking-based traffic performance measurement system for roundabouts and intersections

• Performance measurements are in great need for roundabouts and intersections, which are more challenging than highways (more complex measurement specifications and vehicle behavior)

• Many traditional techniques (using sensors) can only obtain partial performance measurements

[1] T. Kwon, “Portable Cellular Wireless Mesh Sensor Network for Vehicle Tracking in an Intersection”, Minnesota Department of Transportation, Final report, CTS 08-29.

[2] A. Abdel-Rahim, B. Johnson, “An Intersection Traffic Data Collection Device Utilizing Logging Capabilities of Traffic Controllers and Current Traffic Sensors”, National Institute for Advanced Transportation Technology, Final report.

Basic project information

• Traffic performance measurements can be processed offline

• Traffic performance measurements for roundabouts and intersections include: – vehicle volume – vehicle speed (including acceleration/de-acceleration behavior)– origin-destination pairs– waiting time– gap size (by turning or entering vehicles) – lane use, etc

• To apply video/image processing techniques based on probabilistic tracking algorithms to individually track each vehicle from its entrance to exit

Step 1: camera calibration

Actual camera height: 51 feet

Calibrated camera height: 52.4 feet

The height of the camera is 51 feet, which is close to our result (52.36 feet).The height of the camera is 51 feet, which is close to our result (52.36 feet).

Step 2: vehicle tracking for trajectory

The height of the camera is 51 feet, which is close to our result (52.36 feet).The height of the camera is 51 feet, which is close to our result (52.36 feet).

Step 3: data mining for measurements

Start Time

Lane 1Number of Vehicle Average

Travel TimeEnter Exit Remain

1:00:00 PM 7 4 3 15.833331:00:30 PM 3 3 3 12.666671:01:00 PM 2 4 1 17.033331:01:30 PM 0 1 0 13.866671:02:00 PM 4 3 1 17.155561:02:30 PM 4 3 2 11.777781:03:00 PM 7 7 2 16.488891:03:30 PM 4 6 0 12.733331:04:00 PM 16 15 1 10.13333

Intersection Frame

Timegap size

(s)Lane

RelationUpper or

Lowerminute second92 0 13 2.285714 21 1

133 0 19 3.714286 31 2136 0 19 3.285714 31 1229 0 33 6.857143 21 2248 0 35 4.142857 21 2257 0 37 2.857143 21 1444 1 3 5.285714 21 2

1295 3 5 4.285714 21 21416 3 22 4.714286 21 2

93 212 15.86667 143 620 208 9165 258 12.4 136 627 212 9180 274 12.53333 136 628 211 10193 291 13.06667 142 624 216 10366 526 21.33333 134 631 212 11382 549 22.26667 137 629 210 9397 479 10.93333 145 613 206 11475 577 13.6 146 590 211 9682 786 13.86667 142 600 212 9957 1100 19.06667 140 622 216 8971 1100 17.2 143 620 216 7

Lane 1

Start Frame

End Frame

Travel Time

Starting position Ending Positionx y x y

The height of the camera is 51 feet, which is close to our result (52.36 feet).The height of the camera is 51 feet, which is close to our result (52.36 feet).

Results I

2:30 2:40 2:50 3:00 3:10 3:20 3:30 3:40 3:50 4:000

5

10

15

20

Time (PM)

Num

ber

of v

ehic

le e

nter

ing

ram

p 1

4:00 4:20 4:40 5:00 5:20 5:40 6:000

5

10

15

20

Time (PM)

Num

ber

of v

ehic

le e

nter

ing

ram

p 1

2:30 2:40 2:50 3:00 3:10 3:20 3:30 3:40 3:50 4:000

5

10

15

20

Time (PM)

Num

ber

of v

ehic

le e

xitin

g ra

mp1

4:00 4:20 4:40 5:00 5:20 5:40 6:000

5

10

15

20

Time (PM)

Num

ber

of v

ehic

le e

xitin

g ra

mp

1

The height of the camera is 51 feet, which is close to our result (52.36 feet).The height of the camera is 51 feet, which is close to our result (52.36 feet).

Results II

2:30 2:40 2:50 3:00 3:10 3:20 3:30 3:40 3:50 4:000

5

10

15

20

Time (PM)

Wai

ting

time

(sec

ond)

4:00 4:20 4:40 5:00 5:20 5:40 6:000

5

10

15

20

Time (PM)

Wai

ting

time

(sec

ond)

0 5 10 150

5

10

15

20

25

30

35

Gap size (s)

Num

ber

of

occure

nces

0 5 10 150

5

10

15

20

Gap size (s)

Num

ber

of o

ccure

nces

The height of the camera is 51 feet, which is close to our result (52.36 feet).The height of the camera is 51 feet, which is close to our result (52.36 feet).

Computing gap size

(1) For each vehicle, detect when it enters

(2) Record the position of each other vehicle

(3) Compute the distance or travel time

• We have tested more than 50 videos so far.

• The processing time to video length ratio is about 2.

• The vehicle count accuracy and gap size accuracy are over 95% and waiting time accuracy are over 92%.

• The system is subject to more test (origin-destination pairs) and needs to be improved for better accuracy.

Summary and plan

The height of the camera is 51 feet, which is close to our result (52.36 feet).The height of the camera is 51 feet, which is close to our result (52.36 feet).

A commercial system

The height of the camera is 51 feet, which is close to our result (52.36 feet).The height of the camera is 51 feet, which is close to our result (52.36 feet).

Another commercial system

• NATSRL• Dr. Eil Kwon (NATSRL)• District I office• MN-DoT

Acknowledgement