Imagery quantification of damage

• US 9,654,679 B1
• Filed: 03/10/2014
• Issued: 05/16/2017
• Est. Priority Date: 03/13/2013
• Status: Active Grant

• Current Assignee: Liberty Mutual Insurance Company (Liberty Mutual Holding Company)
• Original Assignee: Liberty Mutual Insurance Company (Liberty Mutual Holding Company)
• Inventors: Veliche, Razvan
• Primary Examiner(s): Beaulieu, Yonel
• Assistant Examiner(s): Jos, Basil T
• Application Number:
  US14/202,725
• Time in Patent Office: 1,163 Days
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06T 15/205 Image-based rendering
• CPC Class Codes: G06T 17/20 Finite element generation, e.g. wire-frame surface description, tesselation
• CPC Class Codes: G06T 2200/04 involving 3D image data
• CPC Class Codes: G06T 2200/08 involving all processing steps from image acquisition to 3D model generation
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/55 from multiple images
• CPC Class Codes: H04N 23/64 Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image
• CPC Class Codes: H04N 23/66 Remote control of cameras or camera parts, e.g. by remote control devices

Abstract

A system quantifies the extent of a damaged vehicle in the absence of a specialist (appraiser) present onsite. The system enables an objective estimate of the damage, supplanting or merely supplementing psychologically biased claimant reporting. The system has hardware structures to perform imagery quantification of damage on a damaged vehicle. The damaged vehicle may be located anywhere, including at the scene of an accident, at an insured'"'"'s home, at an insurer'"'"'s claims offices, or at a body shop. Anyone, including the insured, with a mobile device such as a smart phone, may download onto it a mobile application that guides the user to take photographs or moving images of the damaged vehicle for the system to perform imagery quantification of damage.

Claims

1. A system comprising:

a mobile device on which a mobile application executes; and

a photograph-guiding computer, the hardware structure of which is capable of electronically communicating with the mobile application executing on the mobile device to electronically present a grid diagram so as to electronically guide a user to take photographs of a damaged vehicle, the photograph-guiding computer electronically guiding the user of the mobile application being executed on the mobile device to take photographs of the damaged vehicle at a first position including a first distance and at a second position including a second distance.

2. The system of claim 1, wherein the photograph-guiding computer guides the user of the mobile application being executed on the mobile device to take photographs of the damaged vehicle at the first position including the first distance and a first angle and the second position including the second distance and a second angle.

3. The system of claim 2, further comprising a surface damage calculator, the hardware structure of which has the capacity to calculate the surface that has been damaged or the size of the damage on the surfaces of the damaged vehicle.

4. The system of claim 1, further comprising a depth damage calculator, the hardware structure of which is capable of calculating the depth of the damage of the damaged vehicle.

5. The system of claim 4, further comprising a vehicle parts database which provides three-dimensional virtual undamaged parts of the damaged vehicle if the make, model, and year are provided.

6. The system of claim 5, further comprising a damage wireframe computer, the hardware structure of which is suitable for generating a virtual representation of the damaged vehicle.

7. The system of claim 6, further comprising a damage database which is suitable for creating and storing several different size patches selected from a group consisting essentially of 5×

5, 10×

10, and 20×

20 inches, which are virtually cut from the surfaces of the damaged vehicle.

8. A method comprising:

electronically executing a mobile application on a mobile device;

electronically turning on a camera on the mobile device;

electronically displaying a grid diagram on the mobile device;

electronically guiding a user to photograph a damaged vehicle using the grid diagram to produce photographs at a first distance, a first angle, a second distance, and a second angle;

electronically quantifying the photographs taken by the user of the damaged vehicle using the first distance and the second distance to calculate a depth of damage to the damaged vehicle; and

electronically repeating the act of guiding the user if a relative movement of deepest points observed between two or more photographs taken from adjacent but distinct angles will not enable depth calculations.

9. The method of claim 8, wherein quantifying includes calculating a surface of damage to the damaged vehicle.

10. The method of claim 9, further comprising receiving make, model, and year of the damaged vehicle, and extracting three-dimensional parts suitable for the damaged vehicle from a database so as to generate a virtual representation of the damaged vehicle.

11. The method of claim 10, further comprising receiving stereovision analytical instructions so as to analyze the photographs.

12. The method of claim 11, further comprising receiving topological analytical instructions so as to analyze the photographs and quantify an initial depth of damage to the damaged vehicle.

13. The method of claim 12, further comprising using the initial depth estimate to determine whether components of the damaged vehicle within proximity to the surface areas of the damage may have been damaged.

14. The method of claim 13, further comprising determining the distance between a deepest point of the damage and a point on an undamaged virtual surface, both points of which creating a geometric line.

15. The method of claim 14, further comprising estimating a secondary depth of the damage to various parts of the damaged vehicle selected from a group consisting essentially of parts under a hood, parts under a bumper, parts under a door, and parts under panels of the damaged vehicle.

16. The method of claim 15, further comprising building a database of various types and shapes of the damage, and virtually cutting several different size patches selected from a group consisting essentially of 5×

5, 10×

10, and 20×

20 inches.

17. The method of claim 16, further comprising virtually replacing the different size patches with various types of size/depth panels, which are crafted to cover minor damage to the most severe damage.

18. The method of claim 17, further comprising building a wireframe of the damage and indexing the wireframe so that classification and recognition of a specific type of damage can be identified.

19. A non-transitory computer-readable medium having computer-executable instructions stored thereon for implementing a method, comprising:

electronically executing a mobile application on a mobile device;

electronically turning on a camera on the mobile device;

electronically displaying a grid diagram on the mobile device;

electronically guiding a user to photograph a damaged vehicle using the grid diagram to produce photographs at a first angle and a second angle;

electronically quantifying the photographs taken by the user of the damaged vehicle to calculate a depth of damage to the damaged vehicle; and

electronically repeating the act of guiding the user by the photograph-guiding computer if a relative movement of deepest points observed between two or more photographs taken from adjacent but distinct angles will not enable depth calculations.