US 12,272,070 B2
Method and computing system for object identification
Jinze Yu, Tokyo (JP); and Xutao Ye, Tokyo (JP)
Assigned to MUJIN, INC., Tokyo (JP)
Filed by MUJIN, INC., Tokyo (JP)
Filed on Sep. 1, 2023, as Appl. No. 18/460,106.
Application 18/460,106 is a continuation of application No. 16/797,129, filed on Feb. 21, 2020, granted, now 11,763,459.
Application 16/797,129 is a continuation of application No. 16/578,900, filed on Sep. 23, 2019, granted, now 10,614,340, issued on Apr. 7, 2020.
Prior Publication US 2023/0410319 A1, Dec. 21, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/64 (2017.01); G06T 7/12 (2017.01); G06V 10/24 (2022.01); G06V 10/44 (2022.01); G06V 20/64 (2022.01)
CPC G06T 7/12 (2017.01) [G06T 7/64 (2017.01); G06V 10/245 (2022.01); G06V 10/44 (2022.01); G06V 20/64 (2022.01); G06T 2207/10028 (2013.01); G06T 2207/20164 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computing system, comprising:
a non-transitory computer-readable medium; and
at least one processing circuit configured, when three-dimensional (3D) spatial structure data describing object structure is stored in the non-transitory computer-readable medium, to:
identify, from the 3D spatial structure data, a plurality of vertices that describe a contour of the object structure;
identify which of the plurality of vertices satisfies a 3D corner criterion based on the 3D spatial structure data;
identify convex corners associated with the object structure based on the vertices satisfying the 3D corner criterion; and
perform object recognition according to the convex corners.