METHOD AND SYSTEMS OF CLASSIFYING A VEHICLE USING MOTION VECTORS

• US 20140362230A1
• Filed: 06/11/2013
• Published: 12/11/2014
• Est. Priority Date: 10/20/2011
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Bulan, Orhan, Bernal, Edgar A., Loce, Robert P.
• Granted Patent: US 9,286,516 B2
• Time in Patent Office: Days
• US Class Current: 348/169
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles

Abstract

This disclosure provides methods and systems of classifying a vehicle using motion vectors associated with captured images including a vehicle. According to an exemplary method, a cluster of motion vectors representative of a vehicle within a target region is analyzed to determine geometric attributes of the cluster and/or measure a length of a detected vehicle, which provides a basis for classifying the detected vehicle.

Claims

1. A computer-implemented method of classifying a vehicle captured with an image capturing device, the image capturing device oriented to include a field of view spanning a vehicle detection target region, the method comprising:

a) generating a cluster of motion vectors representative of a vehicle detected within the target region;

b) associating one or more attributes with the cluster of motion vectors; and

c) classifying the vehicle detected according to the one or more attributes associated with the cluster of motion vectors.

2. The computer implemented method of classifying a vehicle according to claim 1, wherein the motion vectors are compression type motion vectors.

3. The computer implemented method of classifying a vehicle according to claim 1, wherein step a) generates a cluster of compression type motion vectors representative of a vehicle detected within a virtual target area associated with the image capturing device field of view.

4. The computer implemented method of classifying a vehicle according to claim 1, wherein step c) classifies the vehicle detected as one of a relatively large size vehicle, a relatively small size vehicle, a truck, a bus, a passenger vehicle, and a motorcycle.

5. The computer implemented method of classifying a vehicle according to claim 1, wherein the one or more attributes includes geometrical attributes associated with the cluster of motion vector, the geometrical attributes including one or more of area, length, height, width, and eccentricity.

6. The computer implemented method of classifying a vehicle according to claim 1, wherein the one or more attributes includes a physical length of the detected vehicle obtained by mapping pixel coordinates associated with the cluster of motion vectors to actual units of length.

7. The computer implemented method of classifying a vehicle according to claim 1, wherein the vehicle classification is embedded in compressed data representative of one or more image frames captured with the image capturing device.

8. The computer implemented method of classifying a vehicle according to claim 1, wherein the image capturing device is one of a visible light video camera, infrared video camera, thermal video camera and satellite imaging video camera.

9. An image capturing system for classifying a vehicle captured by the image capturing system, the image capturing system comprising:

an image capturing device oriented to include a field of view spanning a vehicle detection target region; and

an image processor operatively associated with the image capturing device, the image processor configured to perform a method of classifying a vehicle captured with the image capturing device comprising;

a) generating a cluster of motion vectors representative of a vehicle detected within the target region;

b) associating one or more attributes with the cluster of motion vectors; and

c) classifying the vehicle detected according to the one or more attributes associated with the cluster of motion vectors.

10. The image capturing system for classifying a vehicle according to claim 9, wherein the motion vectors are compression type motion vectors.

11. The image capturing system for classifying a vehicle according to claim 9, wherein step a) generates a cluster of compression type motion vectors representative of a vehicle detected within a virtual target area associated with the image capturing device field of view.

12. The image capturing system for classifying a vehicle according to claim 9, wherein step c) classifies the vehicle detected as one of a relatively large size vehicle, a relatively small size vehicle, a truck, a bus, a passenger vehicle, and a motorcycle.

13. The image capturing system for classifying a vehicle according to claim 9, wherein the one or more attributes includes geometrical attributes associated with the cluster of motion vector, the geometrical attributes including one or more of area, length, height, width, and eccentricity.

14. The image capturing system for classifying a vehicle according to claim 9, wherein the one or more attributes includes a physical length of the detected vehicle obtained by mapping pixel coordinates associated with the cluster of motion vectors to actual units of length.

15. The image capturing system for classifying a vehicle according to claim 9, wherein the vehicle classification is embedded in compressed data representative of one or more image frames captured with the image capturing device.

16. The image capturing system for classifying a vehicle according to claim 9, wherein the image capturing device is one of a visible light video camera, infrared video camera, thermal video camera and satellite imaging video camera.

17. A computer implemented method of classifying a vehicle captured with an image capturing device, the image capturing device associated with a field of view including a vehicle detection target region:

a) extracting a cluster of motion vectors representative of a vehicle detected within the target region;

b) associating one or more attributes with the cluster of motion vectors; and

c) classifying the vehicle detected according to the one or more attributes associated with the cluster of motion vectors.

18. The computer implemented method of classifying a vehicle according to claim 17, wherein step c) classifies the vehicle detected as one of a relatively large size vehicle, a relatively small size vehicle, a truck, a bus, a passenger vehicle, and a motorcycle.

19. The computer implemented method of classifying a vehicle according to claim 17, wherein the one or more attributes includes geometrical attributes associated with the cluster of motion vector, the geometrical attributes including one or more of area, length, height, width, and eccentricity.

20. The computer implemented method of classifying a vehicle according to claim 17, wherein the one or more attributes includes a physical length of the detected vehicle obtained by mapping pixel coordinates associated with the cluster of motion vectors to actual units of length.

21. The computer implemented method of classifying a vehicle according to claim 17, wherein the vehicle classification is embedded in compressed data representative of one or more image frames captured with the image capturing device.

22. The computer implemented method of classifying a vehicle according to claim 17, wherein the image capturing device is one of a visible light video camera, infrared video camera, thermal video camera and satellite imaging video camera.

23. An image processing system for classifying a vehicle captured with an image capturing device, the image processing system comprising:

an image processor configured to perform a method comprising;

a) extracting a cluster of motion vectors representative of a vehicle detected within a target region associated with the image capturing device;

b) associating one or more attributes with the cluster of motion vectors; and

c) classifying the vehicle detected according to the one or more attributes associated with the cluster of motion vectors.

24. The image capturing system for classifying a vehicle according to claim 23, wherein the image capturing device is one of a visible light video camera, infrared video camera, thermal video camera and satellite imaging video camera.

25. The image capturing system for classifying a vehicle according to claim 23, wherein the one or more attributes includes geometrical attributes associated with the cluster of motion vector, the geometrical attributes including one or more of area, length, height, width, and eccentricity.

26. The image capturing system for classifying a vehicle according to claim 23, wherein the one or more attributes includes a physical length of the detected vehicle obtained by mapping pixel coordinates associated with the cluster of motion vectors to actual units of length.

27. The image capturing system for classifying a vehicle according to claim 23, wherein the vehicle classification is embedded in compressed data representative of one or more image frames captured with the image capturing device.

28. The image capturing system for classifying a vehicle according to claim 23, wherein the image capturing device is one of a visible light video camera, infrared video camera, thermal video camera and satellite imaging video camera.