Assisted surveillance of vehicles-of-interest

1. A computer-implemented image processing method, the computer including a processor and a memory operatively coupled to the processor, the method performed by the processor comprising:

accessing image data representing a plurality of images of a plurality of vehicles;

accessing a discriminative type-specific vehicle model calculated from training data representing a predefined vehicle attribute;

processing, using the discriminative type-specific vehicle model, a portion of the image data to automatically detect a vehicle feature of at least one of the plurality of vehicles represented in at least one of the plurality of images based on the predefined vehicle attribute; and

processing the portion of the image data to automatically generate vehicle data representing the detected vehicle feature.

2. The computer-implemented method of claim 1 , wherein the discriminative type-specific vehicle model is a part-based mixture model calculated from training data representing the predefined vehicle attribute and wherein the vehicle feature is detected in the portion of the image data using the part-based mixture model.

3. The computer-implemented method of claim 2 , wherein the part-based mixture model is learned using a latent support vector machine.

4. The computer-implemented method of claim 1 , further comprising processing the image data representing the detected vehicle feature to generate a characterization of the vehicle based at least in part on the discriminative type-specific vehicle model.

5. The computer-implemented method of claim 4 , wherein the characterization of the vehicle includes at least one of a predefined vehicle type and a predefined vehicle color.

6. The computer-implemented method of claim 1 , further comprising:

receiving a search query from a user;

processing the vehicle data to search for a vehicle of interest in the plurality of images corresponding to the search query; and

displaying, using a graphical user interface operatively coupled to the processor, the vehicle of interest.

7. The computer-implemented method of claim 6 , further comprising assigning a rank to the vehicle of interest using at least in part the discriminative type-specific vehicle model.

8. The computer-implemented method of claim 1 , further comprising:

using a vehicle detection module to automatically detect at least one of the plurality of vehicles in at least one of the plurality of images;

using a vehicle feature extraction module to automatically detect the vehicle feature and generate the vehicle data;

storing, in the memory, the vehicle data; and

using a search module to query the stored vehicle data and return, based on one or more vehicle feature search parameters, one or more vehicles of interest.

9. An image processing system comprising:

a processor; and

a memory operatively coupled to the processor, the memory having stored therein instructions that when executed by the processor cause the processor to:

access image data representing a plurality of images of a plurality of vehicles;

access a discriminative type-specific vehicle model calculated from training data representing a predefined vehicle attribute;

process, using the discriminative type-specific vehicle model, a portion of the image data to automatically detect a vehicle feature of at least one of the plurality of vehicles represented in at least one of the plurality of images based on the predefined vehicle attribute; and

process the portion of the image data to automatically generate vehicle data representing the detected vehicle feature.

10. The system of claim 9 , wherein:

the discriminative type-specific vehicle model is a part-based mixture model calculated from training data representing the at least one predefined vehicle attribute; and

the vehicle feature is detected in the portion of the image data using the part-based mixture model.

11. The system of claim 10 , wherein:

the part-based mixture model is learned with a latent support vector machine using training images; and

latent variables are associated with negative and/or positive image examples.

12. The system of claim 9 , wherein the memory has further stored therein instructions that when executed by the processor cause the processor to process the image data representing the detected vehicle feature to generate a characterization of the vehicle based at least in part on the discriminative type-specific vehicle model.

13. The system of claim 12 , wherein the characterization of the vehicle includes at least one of a predefined vehicle type and a predefined vehicle color.

14. The system of claim 9 , wherein the memory has further stored therein instructions that when executed by the processor cause the processor to:

receive a search query from a user;

process the vehicle data to search for a vehicle of interest in the plurality of images corresponding to the search query; and

display, using a graphical user interface operatively coupled to the processor, the vehicle of interest.

15. The system of claim 14 , wherein the memory has further stored therein instructions that when executed by the processor cause the processor to assign a rank to the vehicle of interest using at least in part the discriminative type-specific vehicle model.

16. The system of claim 9 , wherein the memory is configured to store the vehicle data, the system further comprising:

a vehicle detection module configured to automatically detect at least one of the plurality of vehicles in at least one of the plurality of images;

a vehicle feature extraction module configured to automatically detect the vehicle feature; and

a search module configured to query the stored vehicle data and return, based on one more vehicle feature search parameters, one or more vehicles of interest.

17. A non-transitory computer readable medium having stored thereon instructions that when executed by a processor cause the processor to:

access image data representing a plurality of images of a plurality of vehicles;

access a discriminative type-specific vehicle model calculated from training data representing a predefined vehicle attribute;

process, using the discriminative type-specific vehicle model, a portion of the image data to automatically detect a vehicle feature of at least one of the plurality of vehicles represented in at least one of the plurality of images based on the predefined vehicle attribute; and

process the portion of the image data to automatically generate vehicle data representing the detected vehicle feature.

18. The non-transitory computer readable medium of claim 17 wherein the discriminative type-specific vehicle model is a part-based mixture model calculated from training data representing the predefined vehicle attribute and wherein the vehicle feature is detected in the portion of the image data using the part-based mixture model.

19. The non-transitory computer readable medium of claim 17 , further having stored thereon instructions that when executed by the processor cause the processor to process the image data representing the detected vehicle feature to generate a characterization of the vehicle based at least in part on the discriminative type-specific vehicle model.

20. The non-transitory computer readable medium of claim 17 , further having stored thereon instructions that when executed by the processor cause the processor to:

receive a search query from a user;

process the vehicle data to search for a vehicle of interest in the plurality of images corresponding to the search query; and

display, using a graphical user interface operatively coupled to the processor, the vehicle of interest.