Method and apparatus for differentiating pedestrians, vehicles, and other objects

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

detecting, with a processor, an object within a region of interest;

matching, with the processor, said object with an object template;

dividing, with the processor, said object into a plurality of sub-regions based on said object template, wherein each sub-region represents a portion of the detected object;

performing, with a processor, edge analysis on each of the plurality of sub-regions within said object to generate an edge score for each of said sub-regions;

summing, with a processor, the edge score for each of said sub-regions; and

classifying, with a processor, said object based on the sum of said edge scores.

2. The method of claim 1 , wherein performing edge analysis comprises performing Canny edge detection.

3. The method of claim 1 , wherein said plurality of sub-regions comprise a top region, a bottom region, a left region, and a right region.

4. The method of claim 1 , wherein said plurality of sub-regions comprise a head region, a left upper body region, a right upper body region, a left lower body region, and a right lower body region.

5. The method of claim 1 , wherein said edge analysis determines an edge density for each sub-region.

6. The method of claim 5 , wherein said sum of said edge scores comprises a sum of the edge density for each sub-region.

7. The method of claim 1 , wherein said object is classified in accordance with a threshold for said sum of said edge scores.

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

means for detecting said object within a region of interest;

means for matching said object with an object template;

means for dividing said object into a plurality of sub-regions based on said object template, wherein each sub-region represents a portion of the detected object;

means for performing edge analysis on said plurality of sub-regions within said object to generate edge scores for each of said sub-regions;

means for summing said edge scores of said sub-regions, thereby generating a sum of said edge scores;

means for classifying said object based on said sum of said edge scores.

9. The apparatus of claim 8 , wherein performing edge analysis comprises performing Canny edge detection.

10. The apparatus of claim 8 , wherein said plurality of sub-regions comprise a top region, a bottom region, a left region, and a right region.

11. The apparatus of claim 8 , wherein said plurality of sub-regions comprise a head region, a left upper body region, a right upper body region, a left lower body region, and a right lower body region.

12. The apparatus of claim 8 , wherein said edge analysis determines an edge density for each sub-region.

13. The apparatus of claim 12 , wherein said sum of said edge scores comprises a sum of the edge density for each sub-region.

14. The apparatus of claim 8 , wherein said object is classified in accordance with a threshold for said sum of said edge scores.

15. 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 of classifying an object in an image, comprising:

detecting said object within a region of interest;

matching, with the processor, said object with an object template;

dividing said object into a plurality of sub-regions based on said object template, wherein each sub-region represents a portion of the detected object;

performing edge analysis on each of the plurality of sub-regions within said object to generate an edge score for each of said sub-regions;

summing the edge score for each of said sub-regions to generate a sum of said edge scores; and

classifying said object based on said sum of said edge scores.

16. The computer-readable medium of claim 15 , wherein performing edge analysis comprises performing Canny edge detection.

17. The computer-readable medium of claim 15 , wherein said plurality of sub-regions comprise a top region, a bottom region, a left region, and a right region.

18. The computer-readable medium of claim 15 , wherein said plurality of sub-regions comprise a head region, a left upper body region, a right upper body region, a left lower body region, and a right lower body region.

19. The computer-readable medium of claim 15 , wherein said edge analysis determines an edge density for each sub-region.

20. The computer-readable medium of claim 15 , wherein said object is classified in accordance with a threshold for said sum of said edge scores.

21. The computer-readable medium of claim 15 , wherein performing edge analysis comprises producing an isometric original edge map.

22. The computer-readable medium of claim 15 , wherein performing edge analysis comprises producing a horizontal edge map.

23. The computer-readable medium of claim 15 , wherein performing edge analysis comprises producing a vertical edge map.

24. The method of claim 1 , wherein performing edge analysis comprises producing an isometric original edge map.

25. The method of claim 1 , wherein performing edge analysis comprises producing a horizontal edge map.

26. The method of claim 1 , wherein performing edge analysis comprises producing a vertical edge map.

27. The apparatus of claim 8 , wherein performing edge analysis comprises producing an isometric original edge map.

28. The apparatus of claim 8 , wherein performing edge analysis comprises producing a horizontal edge map.

29. The apparatus of claim 8 , wherein performing edge analysis comprises producing a vertical edge map.