Vehicle prediction and association tool based on license plate recognition

• US 9,031,948 B1
• Filed: 07/06/2012
• Issued: 05/12/2015
• Est. Priority Date: 07/06/2011
• Status: Active Grant

• Current Assignee: VaaS International Holdings, Inc. (Motorola Solutions, Inc.)
• Original Assignee: VaaS International Holdings, Inc. (Motorola Solutions, Inc.)
• Inventors: Smith, Shawn B.
• Primary Examiner(s): Ruiz, Angelica
• Application Number:
  US13/543,327
• Time in Patent Office: 1,040 Days
• Field of Search: None
• US Class Current: 707/736
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/70 of video data
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names
• CPC Class Codes: G06V 30/10 Character recognition

Abstract

LPR instances around physical locations and license plate numbers associated with a person of interest are analyzed to predict the relative likelihood of locating the person of interest at a particular location. An LPR information query includes an indication of a physical location and a license plate number associated with a person of interest. The relative likelihood of locating a person of interest at a particular location at a future point in time is determined based on the LPR instances received. In one example, the relative likelihood of locating the person of interest is based on the relative value of clusters of LPR instances around physical locations associated with the person of interest. Additional license plate numbers are associated with a person of interest based on their appearance within a search zone and time window of LPR instances of a license plate number already associated with a person of interest.

Claims

1. A method comprising:

receiving a license plate recognition (LPR) information query including an indication of a physical location and a target license plate number;

determining a plurality of license plate recognition (LPR) instances within a search area of the physical location in response to receiving the LPR information query;

determining a first license plate number within a first search zone and a first time window around a first LPR instance of the target license plate number, wherein the first LPR instance comprises an indication of a first physical location of the target license plate number and an indication of a first time when an image of the target license plate number was captured;

determining a second license plate number within a second search zone and a second time window around a second LPR instance of the target license plate number, wherein the second LPR instance comprises an indication of a second physical location of the target license plate number and an indication of a second time when an image of the target license plate number was captured; and

associating the first license plate number and the target license plate number if the first license plate number matches the second license plate number.

2. The method of claim 1, wherein an LPR instance of the plurality of LPR instances includes an indication of a vehicle license plate number, an indication of a physical location, and an indication of a time when the LPR instance was captured by an LPR system.

3. The method of claim 1, wherein the target license plate number is associated with a person of interest.

4. A method comprising:

receiving an indication of a physical location and a license plate number associated with a person of interest;

determining a relative likelihood of locating the person of interest at a particular location based on a plurality of license plate recognition (LPR) instances associated with the physical location and the license plate number, wherein the determining the relative likelihood of locating the person of interest involves;

receiving an indication of a plurality of LPR instances within a search area of the physical location;

determining a plurality of clusters of the plurality of LPR instances;

determining an attribute of each of the clusters based on at least one search metric; and

determining the relative likelihood of locating the person of interest at the physical location based on at least one attribute.

5. The method of claim 4, wherein the determining of a cluster of LPR instances involves:

determining a time difference between successive LPR instances; and

determining if the time difference between successive LPR instances is less than a predetermined threshold.

6. The method of claim 4, wherein the determining of the relative likelihood of locating a person of interest at the physical location involves scaling a value of a cluster based on an amount of time since the last LPR site visit to the physical location.

7. The method of claim 4, wherein the determining of the relative likelihood of locating a person of interest at the physical location involves scaling a value of a cluster based on a number of LPR site visits to the physical location.

8. The method of claim 4, further comprising:

communicating the relative likelihood of locating the person of interest to a user.

9. A method comprising:

receiving an indication of a plurality of License Plate Recognition (LPR) instances;

determining a first license plate number within a first search zone and a first time window around a first LPR instance of a target license plate number, wherein the first LPR instance comprises an indication of a first physical location of the target license plate number and an indication of a first time when an image of the target license plate number was captured;

determining a second license plate number within a second search zone and a second time window around a second LPR instance of the target license plate number, wherein the second LPR instance comprises an indication of a second physical location of the target license plate number and an indication of a second time when an image of the target license plate number was captured; and

associating the first license plate number and the target license plate number if the first license plate number matches the second license plate number.

10. The method of claim 9, wherein the first search zone is an area within a first distance of a physical location of the target license plate number at a time of the first LPR instance, and wherein the second search zone is an area within a second distance of a physical location of the target license plate number at a time of the second LPR instance.

11. The method of claim 10, wherein the first distance is less than one hundred meters.

12. The method of claim 10, wherein the first distance and the second distance are the same distance.

13. The method of claim 9, further comprising:

determining a third license plate number within a third search zone and a third time window around a first license plate recognition (LPR) instance of the first license plate number if the first license plate number is associated with the target license plate number; and

associating the third license plate number and the target license plate number if the third license plate number is determined to be within the first search zone and the first time window around the first license plate recognition (LPR) instance of the target license plate number.

14. The method of claim 13, wherein the association of the first license plate number and the target license plate number is a direct association, and wherein the association of the third license plate number and the target license plate number is an indirect association.

15. An LPR information server comprising:

a processor; and

a memory storing an amount of program code that, when executed causes the LPR information server to

receive a license plate recognition (LPR) information query including an indication of a physical location and a license plate number;

determine a plurality of license plate recognition (LPR) instances within a search area of the physical location in response to receiving the LPR information query;

determine a first license plate number within a first search zone and a first time window around a first LPR instance of the target license plate number, wherein the first LPR instance comprises an indication of a first physical location of the target license plate number and an indication of a first time when an image of the target license plate number was captured;

determine a second license plate number within a second search zone and a second time window around a second LPR instance of the target license plate number, wherein the second LPR instance comprises an indication of a second physical location of the target license plate number and an indication of a second time when an image of the target license plate number was captured; and

associate the first license plate number and the target license plate number if the first license plate number matches the second license plate number.

16. The LPR information server of claim 15, wherein an LPR instance of the plurality of LPR instances includes an indication of a vehicle license plate number, an indication of a physical location, and an indication of a time when the LPR instance was captured by the LPR system.

17. The LPR information server of claim 15, wherein a license plate number associated with each of the plurality of LPR instances matches the license plate number included with the LPR information query.

18. An apparatus comprising:

a processor; and

a memory storing an amount of program code that, when executed causes the apparatus to

receive an indication of a physical location and a license plate number associated with a person of interest; and

determine a relative likelihood of locating the person of interest at a particular location based on a plurality of license plate recognition (LPR) instances associated with the physical location and the license plate number, wherein the determining the relative likelihood of locating the person of interest involves;

receiving an indication of a plurality of LPR instances within a search area of the physical location;

determining a plurality of clusters of the plurality of LPR instances;

determining an attribute of each of the clusters based on at least one search metric; and

determining the relative likelihood of locating the person of interest at the physical location based on at least one attribute.

19. The apparatus of claim 18, wherein the determining of a cluster of LPR instances involves:

determining a time difference between successive LPR instances; and

determining if the time difference between successive LPR instances is less than a predetermined threshold.

20. The apparatus of claim 18, wherein the determining of the relative likelihood of locating a person of interest at the physical location involves scaling a value of a cluster based on an amount of time since the last LPR site visit to the physical location.

21. The apparatus of claim 18, wherein the determining of the relative likelihood of locating a person of interest at the physical location involves scaling a value of a cluster based on a number of LPR site visits to the physical location.

22. An apparatus comprising:

a processor; and

a memory storing an amount of program code that, when executed causes the apparatus to

receive an indication of a plurality of License Plate Recognition (LPR) instances;

determine a first license plate number within a first search zone and a first time window around a first LPR instance of a target license plate number, wherein the first LPR instance comprises an indication of a first physical location of the target license plate number and an indication of a first time when an image of the target license plate number was captured;

determine a second license plate number within a second search zone and a second time window around a second LPR instance of the target license plate number, wherein the second LPR instance comprises an indication of a second physical location of the target license plate number and an indication of a second time when an image of the target license plate number was captured; and

associate the first license plate number and the target license plate number if the first license plate number matches the second license plate number.

23. The apparatus of claim 22, wherein the first search zone is an area within a first distance of a physical location of the target license plate number at a time of the first LPR instance, and wherein the second search zone is an area within a second distance of a physical location of the target license plate number at a time of the second LPR instance.

24. The apparatus of claim 22, the memory also storing an amount of program code that, when executed causes the apparatus to

determine a third license plate number within a third search zone and a third time window around a first license plate recognition (LPR) instance of the first license plate number if the first license plate number is associated with the target license plate number;

and

associate the third license plate number and the target license plate number if the third license plate number is determined to be within the first search zone and the first time window around the first license plate recognition (LPR) instance of the target license plate number.