US 11,681,539 B2
Transforming asset operation video to augmented reality guidance model
Zhe Yan, Beijing (CN); Li Li Guan, Beijing (CN); Hao Jia Li, Beijing (CN); Rong Zhao, Beijing (CN); and Li Bo Zhang, Beijing (CN)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on May 28, 2021, as Appl. No. 17/333,442.
Prior Publication US 2022/0382569 A1, Dec. 1, 2022
Int. Cl. G06F 9/50 (2006.01); G06T 19/00 (2011.01); G06F 9/451 (2018.01); G06T 7/73 (2017.01); G06V 20/40 (2022.01); G06V 20/20 (2022.01)
CPC G06F 9/453 (2018.02) [G06T 7/73 (2017.01); G06T 7/75 (2017.01); G06T 19/006 (2013.01); G06V 20/20 (2022.01); G06V 20/41 (2022.01); G06V 20/48 (2022.01); G06V 20/49 (2022.01); G06T 7/74 (2017.01)] 12 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
detecting a plurality of objects in a video recording associated with completing a task;
generating at least one two-dimensional (2D) image data for each detected object of the detected plurality of objects;
generating a plurality of three-dimensional (3D) object models based on scanning a plurality of real objects in a task space;
generating at least one 3D model data for each 3D object model of the generated plurality of 3D object models;
matching the detected plurality of objects in the video recording with the generated plurality of 3D object models representing the plurality of real objects in the task space; and
generating, based on the video recording, an augmented reality (AR) guidance model for completing the task, wherein the generated AR guidance model replaces the detected plurality of objects in the video recording with the generated plurality of 3D object models representing the plurality of real objects in the task space.