US 12,272,162 B2
Methods and systems of utilizing image processing systems to measure objects
Steven Penny, Chicago, IL (US); Mohan Liu, Chicago, IL (US); Bahar Radfar, Seattle, WA (US); Neda Hantehzadeh, Chicago, IL (US); Bhadresh Dhanani, Chicago, IL (US); Sagar Bachwani, Chicago, IL (US); Ranjini Vaidyanathan, Chicago, IL (US); Masatoshi Kato, Seattle, WA (US); Srinivasan Krishnaswamy, Chicago, IL (US); and Mina Haratiannezhadi, Chicago, IL (US)
Assigned to CCC INTELLIGENT SOLUTIONS INC., Chicago, IL (US)
Filed by CCC INTELLIGENT SOLUTIONS INC., Chicago, IL (US)
Filed on May 10, 2022, as Appl. No. 17/741,073.
Claims priority of provisional application 63/186,717, filed on May 10, 2021.
Prior Publication US 2022/0358634 A1, Nov. 10, 2022
Int. Cl. G06V 20/70 (2022.01); G06F 3/0482 (2013.01); G06Q 10/20 (2023.01); G06Q 30/0283 (2023.01); G06T 3/18 (2024.01); G06T 7/00 (2017.01); G06T 7/10 (2017.01); G06T 7/11 (2017.01); G06T 7/50 (2017.01); G06T 7/70 (2017.01); G06V 10/26 (2022.01); G06V 10/764 (2022.01); G06V 10/766 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 10/94 (2022.01)
CPC G06V 20/70 (2022.01) [G06T 3/18 (2024.01); G06T 7/0002 (2013.01); G06T 7/0004 (2013.01); G06T 7/10 (2017.01); G06T 7/11 (2017.01); G06T 7/50 (2017.01); G06T 7/70 (2017.01); G06V 10/26 (2022.01); G06V 10/764 (2022.01); G06V 10/766 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 10/945 (2022.01); G06F 3/0482 (2013.01); G06Q 10/20 (2013.01); G06Q 30/0283 (2013.01); G06T 2207/20021 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30252 (2013.01); G06V 2201/08 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A method of utilizing an imaging processing system to measure areas of damage of vehicles, the method comprising:
applying, by an image processing system, a heat map model to an image of a damaged vehicle to thereby generate a heat map of the image of the damaged vehicle, the image of the damaged vehicle include a perspective view of the damaged vehicle, the heat map model trained on a plurality of images of a plurality of vehicles to detect vehicle damage on a pixel-by-pixel basis, and the heat map indicative of a respective probability of a presence of damage at a respective physical location of the damaged vehicle depicted by each pixel of the image;
warping, by the image processing system, at least a portion of the image to generate a warped depiction of at least a portion of the damaged area, the warped depiction of the at least the portion of the damaged area having an essentially uniform depth of field;
warping the heat map based on the warping of the at least the portion of the image to generate a warped heat map;
determining, by the image processing system, at least one measurement of a damaged area of the damaged vehicle based on the warped heat map and a depth of field indicator corresponding to the warped at least the portion of the image of the damaged vehicle; and
providing, by the image processing system, an indication of the at least one measurement of the damaged area to an application.