IP Library Granted Patent US 10,740,891
Granted Patent B1
US 10,740,891 · App. 15/160,307 · Granted Aug 11, 2020

Technology for analyzing images depicting vehicles according to base image models

Inventors: Ke Chen (Chicago, IL); John L. Haller (Valencia, CA); Athinodoros S. Georghiades (Strovolos, CY); Takeo Kanade (Sasayama, JP)
Assignee: CCC INFORMATION SERVICES INC.
G06T7/0008G06Q40/08G06T7/001G06T2207/30252
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,740,891
App. No.
15/160,307
Granted
Aug 11, 2020
Kind
B1
Abstract

A method and system for analyzing images of a target vehicle according to a base image model corresponding to the target vehicle. According to certain aspects, the method and system receive a set of images from an electronic device and analyze the set of images to identify the target vehicle and a set of information associated with the target vehicle. The method and system may determine that the set of images does not meet a threshold criteria for further image analysis using a base image model corresponding to the target vehicle. In response, the method and system may generate and transmit a notification to the electronic device indicating that the set of images does not meet the threshold criteria.

Claims (57)

1. A computer-implemented method in a server device of analyzing images, the method comprising:

receiving an initial set of images from an electronic device via a network connection; analyzing at least a portion of the initial set of images to identify (i) a target vehicle that is depicted in the at least the portion of the initial set of images, and (ii) a set of information associated with the target vehicle;

accessing a particular base image model corresponding to the target vehicle; determining, based at least in part on the set of information associated with the target vehicle, that the initial set of images does not collectively meet a threshold criteria corresponding to a completeness, among an entirety of the initial set of images, of a plurality of types of image perspectives required for the particular base image model for further image analysis using the particular base image model, wherein different pluralities of types of image perspectives are required for different base image models;

in response to determining that the initial set of images does not collectively meet the threshold criteria, generating a notification indicating that the entirety of the initial set of images does not collectively meet the threshold criteria, and transmitting the notification to the electronic device via the network connection;

receiving, via the network connection subsequent to the transmitted notification, an additional set of images of the target vehicle; and

performing the further image analysis, using the particular base image model, on a combination of at least a part of the initial set of images and at least a part of the additional set of images to thereby detect damage to the target vehicle.

2. The computer-implemented method of claim 1 , further comprising:

analyzing at least some of the additional set of images to identify an additional set of information associated with the target vehicle; and

determining, based at least in part on the additional set of information associated with the target vehicle, that the combination of the at least the part of the initial set of images and the at least the part of the additional set of images collectively meets the threshold criteria for the further image analysis using the particular base image model.

3. The computer-implemented method of claim 1 , wherein:

analyzing the at least the portion of the initial set of images to identify the set of information associated with the target the vehicle comprises analyzing the at least the portion of the initial set of images to identify a set of perspective views of the target vehicle depicted in the at least the portion of the initial set of images; and

determining that the initial set of images does not collectively meet the threshold criteria for the further image analysis using the particular base image model comprises determining that a set of types of perspective views of the target vehicle included in the set of perspective views of the target vehicle excludes one or more types of image perspectives required for the particular base image model corresponding to the target vehicle.

4. The computer-implemented method of claim 1 , further comprising accessing telematics data associated with the target vehicle, the telematics data indicating damage to a portion of the target vehicle; and wherein:

analyzing the at least the portion of the initial set of images comprises analyzing the at least the portion of the initial set of images to determine that the damage to the portion of the target vehicle is not depicted in the at least the portion of the initial set of images; and

generating the notification comprises generating a notification to capture one or more images depicting the damage to the portion of the target vehicle.

5. The computer-implemented method of claim 1 , further comprising:

accessing telematics data associated with the target vehicle, wherein the telematics data indicates a first notice of loss (FNOL) event associated with the target vehicle has occurred; and in response to accessing the telematics data, requesting the electronic device to transmit the initial set of images.

6. The computer-implemented method of claim 1 , wherein:

analyzing the at least the portion of the initial set of images comprises analyzing the at least the portion of the initial set of images to identify a set of components of the target vehicle depicted in the at least the portion of the initial set of images; and

determining that the initial set of images does not collectively meet the threshold criteria for the further image analysis using the particular base image model comprises determining that the set of components does not match a set of base vehicle components associated with the particular base image model.

7. The computer-implemented method of claim 1 , wherein

determining that the initial set of images does not collectively meet the threshold criteria for the further image analysis using the particular base image model comprises at least one of:

determining that the initial set of images is unable to be aligned with the particular base image model; or

analyzing the initial set of images according to t the particular base image model, wherein the analyzing is indeterminate.

8. The computer-implemented method of claim 1 , wherein the particular base image model is three-dimensional, and wherein at least some of the images included in the initial set of images are two-dimensional.

9. The computer-implemented method of claim 1 , wherein performing the further image analysis, using the particular base image model, on the combination of the at least the part of the initial set of images and the at least the part of the additional set of images to thereby detect the damage to the target vehicle comprises aligning the at least the part of initial set of images and the at least the part of the additional set of images with the particular base image model, and applying one or more convolutional neural networks to one or more portions of the aligned images of the target vehicle to thereby detect the damage to the target vehicle.

10. The computer-implemented method of claim 1 , wherein the method further comprises determining the completeness of the entirety of the initial set of images; and the completeness of the entirety of the initial set of images further corresponds to at least one of: an amount of image perspectives of the target vehicle, an amount of identified vehicle components, or one or more types of identified vehicle components.

11. A system for analyzing images, comprising:

a communication module configured to communicate with an electronic device via a network connection;

a memory storing a set of base images models corresponding to a set of vehicles; and a processor interfaced with the communication module and the memory, and configured to execute a set of instructions to cause the processor to:

receive an initial set of images from an electronic device via the communication module;

analyze at least a portion of the initial set of images to identify (i) a target vehicle that is depicted in the at least the portion of the initial set of images, and (ii) a set of information associated with the target vehicle;

access, from the memory, a particular base image model corresponding to the target vehicle;

determine, based at least in part on the set of information associated with the target vehicle, that the initial set of images does not collectively meet a threshold criteria corresponding to a completeness, among the entirety of the initial set of images, of a plurality of types of image perspective views required for the particular base image model for further image analysis using the particular base image model, wherein different pluralities of types of image perspectives are required for different base image models;

in response to determining that the initial set of images does not collectively meet the threshold criteria, generate a notification indicating that the entirety of the initial set of images does not collectively meet the threshold criteria, and transmit the notification to the electronic device via the communication module;

receive, via the communication module subsequent to the transmitted notification, an additional set of images of the target vehicle; and

perform the further image analysis, using the particular base image model, on a combination of at least a part of the initial set of images and at least a part of the additional set of images to thereby detect damage to the target vehicle.

12. The system of claim 11 , wherein the processor is further configured to:

analyze at least some of the additional set of images to identify an additional set of information associated with the target vehicle; and

determine, based at least in part on the additional set of information associated with the target vehicle, that the combination of the at least the part of the initial set of images and the at least the part of the additional set of images collectively meets the threshold criteria for the further image analysis using the particular base image model.

13. The system of claim 11 , wherein:

the set of information associated with the target vehicle includes a set of perspective views of the target vehicle depicted in at least the portion of the initial set of images; and

the determination that the initial set of images does not collectively meet the threshold criteria for the further image analysis using the particular base image model includes a determination that a set of types of perspective views of the target vehicle included in the set of perspective views of the target vehicle excludes one or more types of image perspectives required for the particular base image model corresponding to the target vehicle.

14. The system of claim 11 , wherein:

the processor is further configured to access telematics data associated with the target vehicle, the telematics data indicating damage to a portion of the target vehicle;

the analysis of the at least the portion of the initial set of images includes an analysis of the at least the portion of the initial set of images to determine that the damage to the portion of the target vehicle is not depicted in the at least the portion of the initial set of images; and

the generated notification includes an indication that a depiction of the damage to the portion of the target vehicle is not included in the initial set of images.

15. The system of claim 11 , wherein the processor is further configured to:

access telematics data associated with the target vehicle, wherein the telematics data indicates that a first notice of loss (FNOL) event associated with the target vehicle has occurred, and

in response to accessing the telematics data, request the electronic device to transmit the initial set of images.

16. The system of claim 11 , wherein:

the analysis of the at least the portion of the initial set of images includes an analysis of the at least the portion of the initial set of images to identify a set of components of the target vehicle depicted in the at least the portion of the initial set of images; and

the determination that the initial set of images does not collectively meet the threshold criteria for the further image analysis using the particular base image model includes a determination that the set of components does not match a set of base vehicle components associated with the particular base image model.

17. The system of claim 11 , wherein the determination that the initial set of images does not collectively meet the threshold criteria for the further image analysis using the particular base image model includes at least one of: a determination that the initial set of images is unable to be aligned with the particular base image model, or a determination that an analysis of the initial set of images according to the particular base image model is indeterminate.

18. The system of claim 11 , wherein the particular base image model is three-dimensional, and wherein at least some of the images included in the initial set of images are two-dimensional.

19. The system of claim 11 , wherein the performance of the further image analysis, using the particular base image model, on the combination of the at least the part of the initial set of images and the at least the part of the additional set of images to thereby detect the damage to the target vehicle comprises an alignment of the at least the part of the initial set of images and the at least the part of the additional set of images the particular base image model, and an application of one or more convolutional neural networks to one or more portions of the aligned images of the target vehicle to thereby detect the damage to the target vehicle.

20. The system of claim 11 , wherein the set of instructions, when executed by the processor, is further configured to determine the completeness among the entirety of the initial set of images; and the completeness of the entirety of the initial set of images further corresponds to at least one of: an amount of image perspectives of the target vehicle, an amount of identified vehicle components, or one or more types of identified vehicle components.

Assignments (8)
CORRECTIVE ASSIGNMENT TO CORRECT THE U.S. PATENT NUMBER 10740890 TO 10740891 PREVIOUSLY RECORDED ON REEL 59153 FRAME 326. ASSIGNOR(S) HEREBY CONFIRMS THE CHANGE OF NAME. Recorded Oct 2, 2024
From: CCC INFORMATION SERVICES INC.
To: CCC INTELLIGENT SOLUTIONS INC.
Reel/Frame 069113/0762 →
CHANGE OF NAME Recorded Feb 16, 2022
From: CCC INFORMATION SERVICES INC.
To: CCC INTELLIGENT SOLUTIONS INC.
Reel/Frame 059153/0326 →
SECURITY AGREEMENT Recorded Sep 21, 2021
From: CCC INTELLIGENT SOLUTIONS, INC.; CCCIS INTERNATIONAL HOLDINGS INC.; AUTO INJURY SOLUTIONS, INC.
To: BANK OF AMERICA, N.A.
Reel/Frame 057554/0555 →
RELEASE OF SECURITY INTEREST AT REEL/FRAME 042374/0224 Recorded Sep 21, 2021
From: JEFFERIES FINANCE LLC
To: CCC INTELLIGENT SOLUTIONS INC. (F/K/A CCC INFORMATION SERVICES, INC.); AUTO INJURY SOLUTIONS, INC.; CCCIS INTERNATIONAL HOLDINGS INC.
Reel/Frame 057555/0563 →
RELEASE OF SECOND LIEN SECURITY INTEREST Recorded Feb 14, 2020
From: NOMURA CORPORATE FUNDING AMERICAS, LLC
To: CCC INFORMATION SERVICES INC.; AUTO INJURY SOLUTIONS, INC.; CCCIS INTERNATIONAL HOLDINGS INC.
Reel/Frame 051934/0658 →
SECOND LIEN SECURITY AGREEMENT Recorded May 2, 2017
From: CCC INFORMATION SERVICES INC.
To: NOMURA CORPORATE FUNDING AMERICAS, LLC, AS ADMINISTRATIVE AGENT
Reel/Frame 042384/0191 →
FIRST LIEN SECURITY AGREEMENT Recorded May 1, 2017
From: CCC INFORMATION SERVICES INC.
To: JEFFERIES FINANCE LLC, AS ADMINISTRATIVE AGENT
Reel/Frame 042374/0224 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 21, 2016
From: CHEN, KE; HALLER, JOHN L.; GEORGHIADES, ATHINODOROS S.; KANADE, TAKEO
To: CCC INFORMATION SERVICES INC.
Reel/Frame 039820/0416 →
Cited By (26)
US 12,211,298 US 12,211,299 US 12,223,684 US 12,236,488 US 12,260,536 US 12,271,929 US 12,272,162 US 12,300,059 US 12,315,017 US 12,315,276 US 12,321,965 US 12,322,259 US 12,380,420 US 12,394,193 US 12,437,389 US 12,437,564 US 12,457,353 US 12,462,635 US 12,475,756 US 12,536,643 US 12,597,004 US 12,608,687 US 12,646,041 US 12,651,470 US 12,657,238 US 12,676,045