Method and apparatus for differentiating pedestrians, vehicles, and other objects
First Claim
Patent Images
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.
4 Assignments
0 Petitions
Accused Products
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.
-
Citations
29 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 24, 25, 26)
-
-
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. - View Dependent Claims (9, 10, 11, 12, 13, 14, 27, 28, 29)
-
-
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. - View Dependent Claims (16, 17, 18, 19, 20, 21, 22, 23)
-
Specification