US 12,293,311 B2
Vehicle damage assessment method, apparatus, and device
Zhiyou Guo, Zhejiang (CN)
Assigned to Advanced New Technologies Co., Ltd., Grand Cayman (KY)
Filed by Advanced New Technologies Co., Ltd., Grand Cayman (KY)
Filed on Jul. 8, 2021, as Appl. No. 17/370,984.
Application 17/370,984 is a continuation of application No. 16/918,888, filed on Jul. 1, 2020, granted, now 11,087,138.
Application 16/918,888 is a continuation of application No. PCT/CN2018/123336, filed on Dec. 25, 2018.
Claims priority of application No. 201810259950.4 (CN), filed on Mar. 27, 2018.
Prior Publication US 2021/0334548 A1, Oct. 28, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/00 (2022.01); G06Q 10/06 (2023.01); G06Q 40/08 (2012.01); G06T 7/00 (2017.01); G06V 20/00 (2022.01); G06V 20/40 (2022.01); G06V 20/58 (2022.01); G08G 1/017 (2006.01); H04N 23/61 (2023.01); G06V 20/62 (2022.01)
CPC G06Q 10/06 (2013.01) [G06Q 40/08 (2013.01); G06T 7/0002 (2013.01); G06V 20/00 (2022.01); G06V 20/46 (2022.01); G06V 20/584 (2022.01); G08G 1/0175 (2013.01); H04N 23/61 (2023.01); G06T 2207/10016 (2013.01); G06T 2207/30248 (2013.01); G06V 20/625 (2022.01); G06V 2201/08 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
collecting a first image of an object, the collecting the first image including:
receiving an initial image of the object;
automatically determining through deep learning whether the initial image contains an identification of the object; and
in response to determining that the initial image contains the identification of the object, automatically capturing a follow-up image of the object through a camera and by automatically aligning a camera lens of the camera with a portion of the object that contains the identification of the object, the portion of the object that contains the identification of the object being determined based on the initial image;
in response to the first image meeting a first threshold, collecting a second image containing a damage to the object; and
assessing the damage to the object based on the second image in response to the second image meeting a second threshold.