US 11,749,029 B2
Gesture language recognition method and apparatus, computer-readable storage medium, and computer device
Zhaoyang Yang, Shenzhen (CN); Xiaoyong Shen, Shenzhen (CN); Yuwing Tai, Shenzhen (CN); and Jiaya Jia, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Guangdong (CN)
Filed on Aug. 31, 2021, as Appl. No. 17/463,301.
Application 17/463,301 is a continuation of application No. PCT/CN2020/098104, filed on Jun. 24, 2020.
Claims priority of application No. 201910650159.0 (CN), filed on Jul. 18, 2019.
Prior Publication US 2021/0390289 A1, Dec. 16, 2021
Int. Cl. G06K 9/00 (2022.01); G06V 40/20 (2022.01); G06N 3/04 (2023.01); G06V 20/40 (2022.01); G06V 40/16 (2022.01); G06F 18/25 (2023.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01); G06V 10/44 (2022.01)
CPC G06V 40/28 (2022.01) [G06F 18/253 (2023.01); G06N 3/04 (2013.01); G06V 10/454 (2022.01); G06V 10/806 (2022.01); G06V 10/82 (2022.01); G06V 20/44 (2022.01); G06V 20/46 (2022.01); G06V 20/49 (2022.01); G06V 40/168 (2022.01); G06V 40/171 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A gesture language recognition method, comprising:
obtaining a first video;
extracting gesture features from frames of images in the first video, each of the gesture features being extracted from a respective one of the frames based on a two-dimensional network model;
extracting gesture change features from the frames of the images in the first video, each of the gesture change features being extracted from a respective one of the frames based on a three-dimensional network model;
extracting gesture language word information from fused features that are determined based on the gesture features extracted based on the two-dimensional network model and the gesture change features extracted based on the three-dimensional network model; and
combining, by processing circuitry, the gesture language word information into a gesture language sentence according to context information corresponding to the gesture language word information.