Method and apparatus for classifying an object

• US 20070237398A1
• Filed: 08/26/2005
• Published: 10/11/2007
• Est. Priority Date: 08/27/2004
• Status: Active Grant

• Current Assignee: ZAMA Innovations LLC
• Original Assignee: Sarnoff Corporation (SRI International, Inc.)
• Inventors: Chang, Peng, Camus, Theodore
• Granted Patent: US 7,466,860 B2
• Time in Patent Office: Days
• US Class Current: 382/224
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• 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: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition

Abstract

A method and apparatus for classifying an object in an image is disclosed. A plurality of sub-classifiers is provided. An object is classified using input from each of the plurality of sub-classifiers.

Claims

1. A method of classifying an object in an image, comprising:

providing a plurality of sub-classifiers, wherein the plurality of sub-classifiers comprises image-based classifiers, and wherein the image-based classifiers comprise one of a contour-based classifier and an edge-based classifier; and

classifying the object using input from each of the plurality of sub-classifiers.

3. The method of claim 1, wherein the sub-classifiers comprise depth-based classifiers.

5. The method of claim 1, wherein said classifying comprises combining the plurality of sub-classifiers using a Bayesian approach.

6. The method of claim 1, wherein said classifying comprises combining the plurality of sub-classifiers using a hybrid classifier.

7. The method of claim 6, wherein said hybrid classifier defines hypotheses;

and uses a likelihood ratio to decide which hypothesis to select.

8. The method of claim 7, wherein a classification decision is made according to:

H₀ if f_k>

0

H₁ otherwise

where H₀ and H₁, are the hypotheses and f_k is the likelihood ratio.

21. The method of claim 3, wherein the depth-based classifiers comprise measuring the peakness of a pedestrian model match.

22. The method of claim 21, wherein the peakness of a pedestrian model match is defined as the ratio of a first pedestrian 3D score and the sum of two pedestrian 3D scores that are adjacent to the first pedestrian 3D score.

23. The method of claim 3, wherein the depth-based classifiers comprise obtaining a ratio of a pedestrian 3D model score and a car 3D model score.

24. The method of claim 3, wherein the depth-based classifiers comprise an eccentricity test.

25. The method of claim 24, wherein the eccentricity test measures the flatness of a target in a depth map.

2. (canceled)

4. (canceled)

9. An apparatus for classifying an object in an image, comprising:

means for providing a plurality of sub-classifiers, wherein the plurality of sub-classifiers comprises image-based classifiers, and wherein the image-based classifiers comprise one of a contour-based classifier and an edge-based classifier; and

means for classifying the object using input from each of the plurality of sub-classifiers.

11. The apparatus of claim 9, wherein the sub-classifiers comprise depth-based classifiers.

13. The apparatus of claim 9, wherein said classifying comprises combining the plurality of sub-classifiers using a Bayesian approach.

14. The apparatus of claim 9, wherein said classifying comprises combining the plurality of sub-classifiers using a hybrid classifier.

15. The apparatus of claim 14, wherein said hybrid classifier defines hypotheses;

and uses a likelihood ratio to decide which hypothesis to select.

16. The apparatus of claim 15, wherein a classification decision is made according to:

H₀ if f_k>

0

H₁ otherwise

where H₀ and H₁, are the hypotheses and f_k is the likelihood ratio.

10. (canceled)

12. (canceled)

17. A computer-readable medium having stored thereon a plurality of instructions, the plurality of instructions including instructions which, when executed by a processor, cause the processor to perform the steps of a method for classifying an object in an image, comprising:

providing a plurality of sub-classifiers, wherein the plurality of sub-classifiers comprises image-based classifiers, and wherein the image-based classifiers comprise one of a contour-based classifier and an edge-based classifier; and

classifying the object using input from each of the plurality of sub-classifiers.

18. The computer-readable medium of claim 17, wherein said classifying comprises combining the plurality of sub-classifiers using a hybrid classifier.

19. The computer-readable medium of claim 18, wherein said hybrid classifier defines hypotheses;

and uses a likelihood ratio to decide which hypothesis to select.

20. The computer-readable medium of claim 19, wherein a classification decision is made according to:

H₀ if f_k>

0

H₁ otherwise

where H₀ and H₁, are the hypotheses and f_k is the likelihood ratio.

26. A method of classifying an object in an image, comprising:

providing a plurality of sub-classifiers, wherein the plurality of sub-classifiers comprises depth-based classifiers; and

classifying the object using input from each of the plurality of sub-classifiers.

27. The method of claim 26, wherein the depth-based classifiers comprise one of a vehicle model three-dimensional block template matching score and a pedestrian model three-dimensional block template matching score.

28. The method of claim 26, wherein the sub-classifiers comprise image-based classifiers.

29. The method of claim 26, wherein the depth-based classifiers comprise measuring the peakness of a pedestrian model match.

30. The method of claim 29, wherein the peakness of a pedestrian model match is defined as the ratio of a first pedestrian 3D score and the sum of two pedestrian 3D scores that are adjacent to the first pedestrian 3D score.

31. The method of claim 26, wherein the depth-based classifiers comprise a ratio of a pedestrian 3D model score and a car 3D model score.

32. The method of claim 26, wherein the depth-based classifiers comprise an eccentricity test.

33. The method of claim 32, wherein the eccentricity test measures the flatness of a target in a depth map.