System and method for providing automotive purchase, insurance quote, and vehicle financing information using vehicle recognition

• US 8,774,465 B2
• Filed: 06/12/2012
• Issued: 07/08/2014
• Est. Priority Date: 06/12/2012
• Status: Active Grant

• Current Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Original Assignee: State Farm Mutual Automobile Insurance Company (State Farm)
• Inventors: Christopulos, Nick U., Anderson, Matthew R., Tofte, Nathan Lee
• Primary Examiner(s): Chen, Wenpeng
• Application Number:
  US13/494,573
• Publication Number:
  US 20130329943A1
• Time in Patent Office: 756 Days
• Field of Search: 382/104, 705/26.3
• US Class Current: 382/104
• CPC Class Codes: G06V 20/20 in augmented reality scenes
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles

Abstract

A system for providing vehicle information at an automobile point of purchase includes a user device having a camera or other image capturing device that is used to capture an image of an automobile. An application on or associated with the image capturing device can either transmit the image to a service provider for processing, or can implement one or more steps in a feature recognition process locally, and thereafter transmit the data to a service provider. In either case, the service provider can then complete the feature recognition processing and identify the automobile from the image. The service provider can then communicate with a make and model database to provide useful information on the vehicle, which can then be transmitted to the user device and conveniently displayed.

Claims

1. A method for use in a network comprising:

with at least one computing device;

receiving data comprising an electronic image of at least a portion of a vehicle from a prospective purchaser,

automatically analyzing the image to identify a license plate area of the image;

based on the identified license late area, automatically identifying a region of interest of the image corresponding to a rear portion of the vehicle around the license plate;

automatically analyzing the region of interest of the image corresponding the rear portion of the vehicle around the license plate using at least one object recognition technique to extract features from the image;

comparing the features extracted from the image with data associated with an image database of reference vehicle images for a plurality of reference vehicles, including features extracted from a region of interest of each reference vehicle image corresponding to a rear portion of the respective reference vehicle around the license plate;

identifying a make and model of the vehicle based on the results of the comparison; and

delivering vehicle-related information to the prospective purchaser based on the identified make and model of the vehicle.

2. A method in accordance with claim 1, wherein the vehicle-related information comprises vehicle-specific information.

3. A method in accordance with claim 1, wherein the vehicle-related information comprises insurance information.

4. A method in accordance with claim 1, wherein the vehicle-related information comprises financing information.

5. A method in accordance with claim 1, wherein the vehicle-related information comprises comparative information associated with a purchase of the vehicle.

6. A method in accordance with claim 1, wherein the vehicle-related information comprises historical information about the vehicle.

7. A method in accordance with claim 1, wherein the vehicle is identified from the image using a global feature based object recognition approach.

8. A method in accordance with claim 1, wherein the vehicle is identified from the image using a local feature based object recognition approach.

9. A method in accordance with claim 1, wherein identifying from the image the license plate area of the electronic image comprises using edge detection.

10. A system for providing information to a purchaser of a vehicle, comprising:

an image capturing device associated with a prospective vehicle purchaser;

at least one processing device in communication with the image capturing device and configured to;

receive an electronic image of at least a portion of a vehicle from the image capturing device, wherein the image is of an exterior portion of a vehicle other than a portion displaying a Vehicle Identification Number,

automatically identifying a license plate area of the image;

based on the identified license plate area, automatically identify from the image a region of interest of the image corresponding to a rear portion of the vehicle around the license plate of the vehicle; and

identify a make and model of the vehicle using at least one object recognition technique, the at least one object recognition technique including comparing features extracted from the region of interest of the image corresponding to the rear portion of the vehicle with data associated with an image database of vehicle images, wherein features extracted from the image comprise features associated with the region of interest around the license plate of the vehicle other than a Vehicle Identification Number; and

automatically access information from a database corresponding to the make and model of the vehicle identified from the image and deliver the information to the prospective vehicle purchaser.

11. A system in accordance with claim 10, wherein the at least one processing device is configured to identify the vehicle using a scale invariant feature transform based method.

12. A system in accordance with claim 10, wherein the at least one processing device is configured to identify the vehicle using a speeded-up robust features based method.

13. A system in accordance with claim 10, wherein vehicle identification comprises an identification of an individual vehicle, and the information comprises a history of the individual vehicle.

14. A system in accordance with claim 10, wherein a vehicle identification comprises an identification of a make and model of a vehicle, and the information comprises information associated with a vehicle of the same make and model.

15. A system in accordance with claim 10, wherein the information comprises insurance-related information.

16. A system in accordance with claim 10, wherein the information comprises financing-related information.

17. A system in accordance with claim 10, wherein the processing device is configured to identify from the image the license plate area of the electronic image comprises using edge detection.

18. A method for use with non-transitory computer readable media operable on one or more processors, the method comprising:

receiving data comprising an electronic image of at least a portion of a vehicle from a prospective purchaser,

automatically analyzing the image to identify a license plate area of the image;

based on the identified license plate area, automatically identifying a region of interest of the image corresponding to a rear portion of the vehicle around the license plate;

identifying a make and model of the vehicle from features extracted from the region of interest of the image corresponding the rear portion of the vehicle around the license plate using at least one object recognition technique for comparing the extracted features with data from an image database of vehicle images, wherein features extracted from the image comprise features associated with the region of interest around the license plate of the vehicle other than a Vehicle Identification Number; and

providing information to the prospective vehicle purchaser from a database corresponding to identified make and model of the vehicle identified.

19. A method in accordance with claim 18, wherein the identifying comprises identifying the vehicle using a scale invariant feature transform based method.

20. A method in accordance with claim 18, wherein the identifying comprises identifying the vehicle using a speeded-up robust features based method.

21. A method in accordance with claim 18, wherein identifying the vehicle comprises identifying an individual vehicle, and the information comprises a history of the individual vehicle.

22. A method in accordance with claim 18, wherein identifying the vehicle comprises identifying a make and model of a vehicle, and the information comprises information associated with a vehicle of the same make and model.

23. A method in accordance with claim 18, wherein identifying from the image the license plate area of the electronic image comprises using edge detection.

24. A method of vehicle identification and provision of vehicle information, the method comprising:

receiving an electronic image of at least a portion of a vehicle from an image capturing device,

providing a database of reference vehicle images of a plurality of reference vehicles and a vehicle information database;

automatically analyzing the image to identify a license plate area of the image;

based on the identified license plate area, automatically identifying a region of interest of the image corresponding to a rear portion of the vehicle;

using at least one object recognition technique other than character recognition to identify objects/features of the vehicle from the region of interest of the image corresponding to a rear portion of the vehicle; and

comparing the identified objects/features of the vehicle with objects/features identified from the reference vehicle images stored in the database;

identifying the vehicle imaged by the image capturing device based on the comparing of objects/features; and

providing information from the vehicle information database corresponding to the identified vehicle imaged by the image capturing device.

25. A method in accordance with claim 24, wherein the comparing via an object/feature based method comprises a global feature based object recognition method.

26. A method in accordance with claim 24, wherein the comparing via an object/feature based method comprises a local feature based object recognition method.

27. A method in accordance with claim 24, wherein the comparing via an object/feature based method comprises a scale invariant feature transform based method.

28. A method in accordance with claim 24, wherein the comparing via an object/feature based method comprises a speeded-up robust features based method.

29. A method in accordance with claim 24, wherein identifying from the image the license plate area of the electronic image comprises using edge detection.