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

• US 7,672,514 B2
• Filed: 03/02/2005
• Issued: 03/02/2010
• Est. Priority Date: 03/02/2004
• Status: Active Grant

• Current Assignee: ZAMA Innovations LLC
• Original Assignee: Sarnoff Corporation (SRI International, Inc.)
• Inventors: Chang, Peng, Camus, Theodore Armand
• Primary Examiner(s): TUCKER, WESLEY J
• Application Number:
  US11/070,613
• Publication Number:
  US 20050232491A1
• Time in Patent Office: 1,826 Days
• Field of Search: 382/103, 382/104, 382/199, 382/203, 382/266
• US Class Current: 382/199
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands

Abstract

A method and apparatus for classifying an object in an image is disclosed. Edges of an object are detected within a region of interest. Edge analysis is performed on a plurality of sub-regions within the region of interest to generate an edge score. The object is classified based on the edge score.

Claims

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.

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.

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.

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.

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.