Methods and systems for improving yield in wanted vehicle searches

• US 8,582,819 B2
• Filed: 04/27/2012
• Issued: 11/12/2013
• Est. Priority Date: 11/18/2011
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Sandhawalia, Harsimrat, Saunders, Craig, Kozitsky, Vladimir, Islam, Abu, Deppen, John, Bala, Raja, Rodriguez Serrano, Jose Antonio, Burrry, Aaron Michael
• Primary Examiner(s): Ahmed, Samir
• Assistant Examiner(s): Harandi, Siamak
• Application Number:
  US13/458,464
• Publication Number:
  US 20130129152A1
• Time in Patent Office: 564 Days
• Field of Search: None
• US Class Current: 382/105
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06V 10/772 Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images
• CPC Class Codes: G06V 20/625 License plates

Abstract

In response to determining that a target vehicle is at large, identification information associated with the target vehicle'"'"'s license plate may be retrieved and used to generate one or more synthetic license plate images. The synthetic license plate images may be subjected to one or more transformation to cause them to resemble authentic license plate image captures and/or to mimic authentic license plate image captures from existing and operational ALPR system cameras. Target signatures may then be calculated from the synthetic license plate images. Upon capturing an authentic license plate image using an ALPR system camera, a signature of the authentic license plate image may be calculated. If a match is found between the signature of the authentic license plate image and a target signature, law enforcement may be alerted that the target vehicle was detected at the location of the ALPR system camera.

Claims

1. A computer-implemented method of detecting a target vehicle, the method comprising:

receiving identification information associated with a target vehicle;

generating, using a processor, a set of target signatures, wherein generating the set of target signatures comprises;

generating a set of synthetic license plate images using the identification information; and

for each synthetic license plate image in the set of synthetic license plate images, calculating a target signature representing a signature of the synthetic license plate image;

receiving an authentic license plate image, wherein the authentic license plate image was captured by a camera at a location;

calculating a search signature representing a signature of the authentic license plate image;

determining that the search signature matches a target signature from among the set of target signatures; and

determining that the target vehicle was detected at the location based on determining that the search signature matches the target signature.

2. The method of claim 1, wherein generating the set of synthetic license plate images comprises:

retrieving a blank license plate template associated with the identification information;

obtaining character font, size, and color characteristics associated with the license plate template; and

rendering license plate characters associated with the identification information onto the license plate template in conformance with the obtained character font, size, and color characteristics to generate an initial synthetic license plate image.

3. The method of claim 2, wherein generating the set of synthetic license plate images further comprises:

applying one or more transformations to the initial synthetic license plate image to cause the initial synthetic license plate image to resemble an authentic license plate image capture.

4. The method of claim 2, wherein generating the set of synthetic license plate images further comprises:

applying a plurality of different transformations to the initial synthetic license plate image to generate a plurality of synthetic license plate images that resemble different authentic license plate image captures.

5. The method of claim 2, wherein generating the set of synthetic license plate images further comprises:

applying one or more transformations to the initial synthetic license plate images to cause the initial synthetic license plate image to resemble an authentic license plate image capture according to characteristics of an existing and operational ALPR system camera.

6. The method of claim 2, wherein generating the set of synthetic license plate images further comprises:

applying a plurality of different transformations to the initial synthetic license plate images to cause the initial synthetic license plate image to resemble a plurality of different authentic license plate image captures according to different characteristics of a plurality of different existing and operational ALPR system cameras.

7. The method of claim 1, further comprising:

storing the set of target signatures within a target signature data store.

8. The method of claim 7, further comprising:

storing the search signature within the target signature data store.

9. The method of claim 8, further comprising:

determining a measure of similarity between the search signature and one or more target signatures in the target signature data store; and

removing one or more target signatures from the target signature data store having measures of similarity below a specified threshold.

10. The method of claim 8, further comprising:

applying one or more transformations to the authentic image to generate a set of transformed images;

computing a set of new target signatures from the set of transformed images; and

storing the set of new target signatures within the target signature data store.

11. A system configured to implement to detect a target vehicle, the system comprising:

a processing system comprising one or more processors; and

a memory system comprising one or more computer-readable media, wherein the computer-readable media contain instructions stored thereon that, when executed by the processing system, cause the processing system to perform operations comprising;

receiving identification information associated with a target vehicle;

generating a set of target signatures, wherein generating the set of target signatures comprises;

generating a set of synthetic license plate images using the identification information; and

for each synthetic license plate image in the set of synthetic license plate images, calculating a target signature representing a signature of the synthetic license plate image;

receiving an authentic license plate image, wherein the authentic license plate image was captured by a camera at a location;

calculating a search signature representing a signature of the authentic license plate image;

determining that the search signature matches a target signature from among the set of target signatures; and

determining that the target vehicle was detected at the location based on determining that the search signature matches the target signature.

12. The system of claim 11, wherein generating the set of synthetic license plate images comprises:

retrieving a blank license plate template associated with the identification information;

obtaining character font, size, and color characteristics associated with the license plate template; and

rendering license plate characters associated with the identification information onto the license plate template in conformance with the obtained character font, size, and color characteristics to generate an initial synthetic license plate image.

13. The system of claim 12, wherein generating the set of synthetic license plate images further comprises:

applying one or more transformations to the initial synthetic license plate image to cause the initial synthetic license plate image to resemble an authentic license plate image capture.

14. The system of claim 12, wherein generating the set of synthetic license plate images further comprises:

applying a plurality of different transformations to the initial synthetic license plate image to generate a plurality of synthetic license plate images that resemble different authentic license plate image captures.

15. The system of claim 12, wherein generating the set of synthetic license plate images further comprises:

applying one or more transformations to the initial synthetic license plate images to cause the initial synthetic license plate image to resemble an authentic license plate image capture according to characteristics of an existing and operational ALPR system camera.

16. The system of claim 12, wherein generating the set of synthetic license plate images further comprises:

applying a plurality of different transformations to the initial synthetic license plate images to cause the initial synthetic license plate image to resemble a plurality of different authentic license plate image captures according to different characteristics of a plurality of different existing and operational ALPR system cameras.

17. The system of claim 11, the operations further comprising:

storing the set of target signatures within a target signature data store.

18. The system of claim 17, the operations further comprising:

storing the search signature within the target signature data store.

19. The system of claim 18, the operations further comprising:

determining a measure of similarity between the search signature and one or more target signatures in the target signature data store; and

removing one or more target signatures from the target signature data store having measures of similarity below a specified threshold.

20. The system of claim 18, the operations further comprising:

applying one or more transformations to the authentic image to generate a set of transformed images;

computing a set of new target signatures from the set of transformed images; and

storing the set of new target signatures within the target signature data store.