Vehicle data collection and verification

• US 9,710,977 B2
• Filed: 12/23/2016
• Issued: 07/18/2017
• Est. Priority Date: 06/25/2012
• Status: Active Grant

• Current Assignee: Mile Auto, Inc.
• Original Assignee: Vehcon, Inc.
• Inventors: Blumer, Frederick T., Fuller, Joseph R.
• Primary Examiner(s): Shafi, Muhammad
• Application Number:
  US15/390,207
• Publication Number:
  US 20170109948A1
• Time in Patent Office: 207 Days
• Field of Search: 701 1, 701400-541, 340988-996
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06V 20/59 inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
• CPC Class Codes: G06V 2201/02 Recognising information on displays, dials, clocks
• CPC Class Codes: G06V 2201/08 Detecting or categorising vehicles
• CPC Class Codes: G07C 5/0866 the electronic data carrier being a digital video recorder in combination with video camera

Abstract

Disclosed are various embodiments for a data aggregation application. Operational data and image data may be captured from a client device. Odometer readings can be extracted from the image data. The operational data and image data can be verified by comparing an instrument panel depicted in the image data to a known instrument panel depiction.

Claims

1. A system, comprising:

at least one computing device, configured to at least;

obtain, from a mobile device, at least one image capturing an image of at least a portion of a vehicle;

generate from the image of the at least a portion of a vehicle image data of a feature of the vehicle and image data of an odometer display of the vehicle;

generate from the image data of the odometer display an odometer reading;

verify that the vehicle corresponds to a vehicle identification as a function of the image data of a feature of the vehicle by comparing the image data of the feature of the vehicle to an image knowledge base, wherein the at least one image is a first at least one image of the vehicle and the image knowledge base comprises a second at least one image depicting at least a portion of the vehicle, and finding a match between the second at least one image depicting at least a portion of the vehicle and the image data of a feature of the vehicle of the first at least one image of the at least a portion of the vehicle; and

associate the odometer reading with the vehicle identification.

2. The system of claim 1, wherein the second at least one image depicting at least a portion of the vehicle corresponds to a shared make, model or year of the vehicle.

3. The system of claim 1, wherein the at least one computing device is further configured to at least associate the odometer reading with an account corresponding to the vehicle.

4. The system of claim 1, wherein the at least one computing device is further configured to determine from the odometer reading a difference between a temporally earlier odometer reading obtained from a prior obtained image of the vehicle taken at a first point in time and the odometer reading taken at a subsequent second point in time.

5. The system of claim 4, wherein the difference is the number of miles the vehicle was driven between the first point in time and the second point in time.

6. The system of claim 1, wherein the at least one computing device is further configured to at least:

obtain, from the mobile device, operational data associated with a usage of the vehicle; and

associate the operational data with an account corresponding to the vehicle.

7. The system of claim 1, wherein the at least one computing device is further configured to determine whether the first at least one image comprises altered or transformed image data.

8. The system of claim 1, wherein comparing the image data of a feature of the vehicle to the image knowledge base is performed based at least in part on a machine learning algorithm or an image matching algorithm.

9. A method, comprising:

obtaining, by at least one computing device, from a mobile device, at least one image capturing an image of at least a portion of a vehicle;

generating from the image of at least a portion of a vehicle image data of a feature of the vehicle and image data of an odometer display;

generating from the image data of the odometer display an odometer reading;

verifying, by the at least one computing device, that the vehicle corresponds to a vehicle identification as a function of the image data of a feature of the vehicle by comparing the image data of the feature of the vehicle to an image knowledge base, wherein the at least one image is a first at least one image of the vehicle and the image knowledge base comprises a second at least one image depicting the vehicle, and finding a match between the second at least one image depicting at least a portion of the vehicle and the image data of a feature of the vehicle of the first at least one image of the vehicle; and

associating the odometer reading with the vehicle identification.

10. The method of claim 9, wherein the second at least one image depicting at least a portion of the vehicle corresponds to a shared make, model or year of the vehicle.

11. The method of claim 10, further comprising associating, by the at least one computing device, the odometer reading with an account corresponding to the vehicle.

12. The method of claim 10, further comprising:

obtaining, by the at least one computing device, from the mobile device, operational data associated with a usage of the vehicle; and

associating, by the at least one computing device, the operational data with an account corresponding to the vehicle.

13. The method of claim 10, further comprising determining, by the at least one computing device, whether the first at least one image comprises altered or transformed image data.

14. The method of claim 10, wherein comparing the at least one image of a feature of the vehicle to the image knowledge base is performed based at least in part on a machine learning algorithm or an image matching algorithm.

15. The method of claim 9, further comprising determining by the at least one computing device, a difference between the odometer reading and an odometer reading obtained from a temporally earlier odometer reading obtained from a prior image of the vehicle taken at a first point in time and the odometer reading taken at a subsequent second point in time.

16. The method of claim 15, wherein the difference is the number of miles the vehicle was driven between the first point in time and the second point in time.