COLLECTING INFORMATION RELATING TO IDENTITY PARAMETERS OF A VEHICLE

• US 20140064564A1
• Filed: 11/04/2013
• Published: 03/06/2014
• Est. Priority Date: 08/05/2010
• Status: Active Grant

• Current Assignee: Hi-Tech Solutions Incorporated
• Original Assignee: Hi-Tech Solutions Incorporated
• Inventors: Hofman, Yoram, Levy, Shai, Weissman, Shay
• Granted Patent: US 9,245,203 B2
• Time in Patent Office: Days
• US Class Current: 382/105
• CPC Class Codes: G06F 18/24323 Tree-organised classifiers
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names

Abstract

The present invention discloses methods and systems for collecting information relating to identity parameters of a vehicle. According to the invention an image of the vehicle is obtained. A sub-image within the image is identified, interest points within the sub-image are detected and the sub-image is processed so as to obtain descriptors representing the interest points. The descriptors are matched to predetermined descriptors representing interest points in previously obtained images respective of known identity parameters and the information is stored in a record representing an identity of the vehicle.

Claims

1-18. -18. (canceled)

19. A method comprising:

obtaining one or more images of a vehicle;

detecting one or more interest points within at least one of the one or more images;

for at least one of the one or more interest points, processing the at least one of the one or more images to determine one or more descriptors, the one or more descriptors comprising one or more representations of the at least one of the one or more interest points;

matching, with a processor, at least one of the one or more of the descriptors to one or more templates, each of the one or more templates comprising one or more descriptors determined in relation to one or more previously obtained images;

calculating a confidence measure of a match between the at least one of the one or more of the descriptors and at least one of the one or more of the templates; and

identifying one or more identity parameters of the vehicle based on the confidence measure.

20. The method of claim 19, further comprising processing the at least one of the one or more images to produce at least one sub-image, the at least one sub-image comprising an area of the at least one of the one or more images that contains at least one of the one or more identity parameters of the vehicle.

21. The method of claim 20, wherein detecting one or more interest points comprises detecting one or more interest points that relates to at least one of the one or more identity parameters.

22. The method of claim 20, wherein the one or more images comprises a plurality of images, wherein processing the at least one of the one or more images comprises processing at least one sub-image for each of the plurality of images, wherein detecting one or more interest points comprises detecting one or more interest points within each of the at least one sub-images, the method further comprising:

selecting one or more common interest points from among the detected interest points, the one or more common interest points being present in more than one of the sub-images;

wherein matching one or more of the descriptors comprises searching for the one or more common interest points within the one or more templates and selecting at least one template based on an identification of the one or more common interest points within the at least one template.

23. The method of claim 22, wherein the calculating a confidence measure comprises calculating the confidence measure based on the one or more common interest points.

24. The method of claim 20, wherein processing the at least one of the one or more images comprises identifying a Region of Interest (ROI) within the at least one of the one or more images in which an identity parameter is present.

25. The method of claim 19, further comprising:

analyzing at least one of the one or more images to determine a string corresponding to a license plate; and

identifying one or more colors included within the license plate.

26. The method of claim 19, wherein calculating a confidence measure comprises calculating a confidence measure based on a number of repeating interest points in at least one of (a) the at least one of the one or more images or (b) a sub-image of the at least one of the one or more images.

27. The method of claim 19, wherein the one or more interest points comprise one or more one or more points located at least one of (a) within a maker icon of the vehicle present within the at least one of the one or more images, or (b) adjacent to the maker icon of the vehicle the at least one of the one or more images.

28. The method of claim 19, wherein the one or more interest points comprise one or more corners of a maker icon of the vehicle present within the at least one of the one or more images.

29. The method of claim 19, wherein the one or more interest points represent changes in brightness within the at least one of the one or more images in at least one of a horizontal direction or a vertical direction.

30. The method of claim 19, wherein the at least one of the one or more templates comprises a vector of descriptors.

31. The method of claim 30, wherein the vector of descriptors represents a neighborhood of an interest point.

32. The method of claim 19, wherein at least one of the one or more identity parameters of the vehicle comprises at least one of:

a maker icon of the vehicle,

a grille shape of the vehicle,

a head lights shape of the vehicle,

a tail lights shape of the vehicle,

a model icon of the vehicle,

a body color of the vehicle,

a vehicle make of the vehicle,

a vehicle model of the vehicle,

a lights shape of the vehicle,

a license plate characteristic of the vehicle,

a sticker of the vehicle, or

an emblem of the vehicle.

33. The method of claim 19, further comprising selecting the one or more templates.

34. The method of claim 33, wherein selecting the one or more templates comprises selecting the one or more templates based on a failure of a license plate recognition process.

35. The method of claim 33, wherein selecting the one or more templates comprises selecting the one or more templates based on a failure of a vehicle icon recognition process.

36. A system comprising:

a memory; and

a processor, coupled to the memory, to;

obtain one or more images of a vehicle;

detect one or more interest points within at least one of the one or more images;

for at least one of the one or more interest points, process the at least one of the one or more images to determine one or more descriptors, the one or more descriptors comprising one or more representations of the at least one of the one or more interest points;

match at least one of the one or more of the descriptors to one or more templates, each of the one or more templates comprising one or more descriptors determined in relation to one or more previously obtained images;

calculate a confidence measure of a match between the at least one of the one or more of the descriptors and at least one of the one or more of the templates; and

identify one or more identity parameters of the vehicle based on the confidence measure.

37. The system of claim 36, wherein the processor is further to:

obtaining at least one image of a license plate of the vehicle;

analyze at least one of the one or more images to determine a string corresponding to a license plate; and

identify one or more colors included within the license plate.

38. A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by a processor cause the processor to perform operations comprising:

obtaining one or more images of a vehicle;

detecting one or more interest points within at least one of the one or more images;

for at least one of the one or more interest points, processing the at least one of the one or more images to determine one or more descriptors, the one or more descriptors comprising one or more representations of the at least one of the one or more interest points;

matching, with the processor, at least one of the one or more of the descriptors to one or more templates, each of the one or more templates comprising one or more descriptors determined in relation to one or more previously obtained images;

calculating a confidence measure of a match between the at least one of the one or more of the descriptors and at least one of the one or more of the templates; and

identifying one or more identity parameters of the vehicle based on the confidence measure.

39. The non-transitory computer storage medium of claim 38, further encoded with a computer program that comprises instructions that when executed by the processor cause the processor to perform operations comprising:

analyzing at least one of the one or more images to determine a string corresponding to a license plate; and

identifying one or more colors included within the license plate.