System and method for vehicle detection and tracking

• US 20040131233A1
• Filed: 06/17/2003
• Published: 07/08/2004
• Est. Priority Date: 06/17/2002
• Status: Active Grant

• Current Assignee: Siemens Corp. (Siemens AG)
• Original Assignee: Siemens Corporate Research Incorporated (Siemens AG)
• Inventors: Ramesh, Visvanathan, Comaniciu, Dorin, Paragios, Nikolaos
• Granted Patent: US 6,999,004 B2
• Time in Patent Office: Days
• US Class Current: 382/104
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G08G 1/04 using optical or ultrasonic detectors

Abstract

A system and method for vehicle detection and tracking in tunnels is provided. The method comprises the steps of capturing a plurality of image frames viewing at least one traffic lane; extracting at least one feature from the plurality of image frames; detecting at least one object indicative of a vehicle from the extracted feature; and tracking the detected vehicle over time to determine the detected vehicle'"'"'s velocity. The system comprising at least one image capture device for capturing a plurality of image frames viewing at least one traffic lane; and a processor adapted for extracting at least one feature from the plurality of image frames, detecting at least one object indicative of a vehicle from the extracted feature, and tracking the detected vehicle over time to determine the detected vehicle'"'"'s velocity.

Claims

1. A method for vehicle detection and tracking, the method comprising the steps of:

capturing a plurality of image frames viewing at least one traffic lane;

extracting at least one feature from the plurality of image frames;

detecting at least one object indicative of a vehicle from the extracted feature; and

tracking the detected vehicle over time to determine the detected vehicle'"'"'s velocity.

2. The method as in claim 1, wherein a detection line is defined for the at least one traffic lane.

3. The method as in claim 2, wherein the extracting step comprises:

calculating a positive spatial gradient for each of the plurality of frames;

calculating temporal differences between the spatial gradients of neighboring frames; and

performing convolutions along the detection line of the at least one traffic lane for extracting the at least one feature.

4. The method of claim 3, wherein the performing convolutions step comprises:

performing a first convolution for testing motion discontinuity of the extracted feature with a first, two-dimensional kernel; and

performing a second convolution for testing symmetry of the observed motion with a second, two-dimensional kernel.

5. The method of claim 4, wherein the extracting step further comprises subtracting the absolute value of the result of the second convolution from a result of the first convolution resulting in an objective function.

6. The method of claim 4, wherein the first kernel having a width of a predetermined vehicle and a height of one and half times the predetermined vehicle and the second kernel having a width and height of the predetermined vehicle.

7. The method of claim 5, wherein the detecting step comprises:

determining a maximum value along the detection line of the objective function, wherein the maximum is indicative of the detected vehicle.

8. The method of claim 7, wherein the detecting step comprises:

analyzing the maximum value along the temporal dimension by comparing the maximum value to a first threshold to ensure the maximum value is at a peak.

9. The method of claim 8, wherein the detecting step further comprises:

imposing an isolation criteria in time to the determined maximum value; and

removing false responses from the neighboring region.

10. The method as in claim 1, wherein the tracking step comprises the steps of:

determining a direction of the detected vehicle; and

comparing the determined direction to a predetermined direction, whereby confirming the detected vehicle is going in the right direction.

11. The method as in claim 1, further comprising the step of counting a number of detected vehicles over a predetermined period of time.

12. A system for vehicle detection and tracking, the system comprising:

at least one image capture device for capturing a plurality of image frames viewing at least one traffic lane; and

a processor adapted for extracting at least one feature from the plurality of image frames, detecting at least one object indicative of a vehicle from the extracted feature, and tracking the detected vehicle over time to determine the detected vehicle'"'"'s velocity.

13. The system of claim 12, wherein the processor is adapted for defining a detection line for the at least one traffic lane.

14. The system as in claim 13, wherein the processor is further adapted for calculating a positive spatial gradient for each of the plurality of frames, calculating temporal differences between the spatial gradients of neighboring frames, and performing convolutions along the detection line of the at least one traffic lane for extracting the at least one feature.

15. The system of claim 14, wherein the processor is further adapted for performing a first convolution for testing motion discontinuity of the extracted feature with a first, two-dimensional kernel, and performing a second convolution for testing symmetry of the observed motion with a second, two-dimensional kernel.

16. The system of claim 15, wherein the processor is further adapted for subtracting the absolute value of the result of the second convolution from a result of the first convolution resulting in an objective function.

17. The system of claim 16, wherein the processor is further adapted for determining a maximum value along the detection line of the objective function, wherein the maximum is indicative of the detected vehicle.

18. The system as in claim 12, wherein the processor is adapted for determining a direction of the detected vehicle and comparing the determined direction to a predetermined direction, further comprising an annunciating device for issuing an alert when the detected vehicle is going in a direction opposite the predetermined direction.

19. The system as in claim 12, wherein the processor is adapted for determining if the detected vehicle is stopped, further comprising an annunciating device for issuing an alert when the detected vehicle is determined to be stopped.

20. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform the method steps for vehicle detection and tracking, the method steps comprising:

capturing a plurality of image frames viewing at least one traffic lane;

extracting at least one feature from the plurality of image frames;

detecting at least one object indicative of a vehicle from the extracted feature; and

tracking the detected vehicle over time to determine the detected vehicle'"'"'s velocity.