Method and system for hand pose recognition, device and storage medium

US11688098B2 · kind B2 · utility

Assignee

• NATIONAL UNIVERSITY OF DEFENSE TECHNOLOGY · CN

Inventors

• Jie Jiang · Shanghai, CN
• Yang Liu · Nanhu, CN
• Xianghan WANG · Hunan, CN
• Jiahao SUN · Hunan, CN
• Junyan Yang · 安丰镇, CN
• Yixiang He · Hunan, CN
• Liang Bai · Beijing, CN
• Lai O Kang · Osan-si, KR
• Yingmei Wei · Hunan, CN
• Yuxiang Xie · Hunan, CN

Key dates

• Filing date: Sep 2, 2022
• Grant date: Jun 27, 2023
• Expiry date: Sep 2, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G06T2207/30196
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

The disclosure relates to a method and a system for hand pose recognition, a device and a storage medium are disclosed in embodiments of the disclosure. The method includes: capturing a RGB image of a hand from a RGB camera and capturing a depth image of the hand from an active depth camera, so as to obtain a hand pose data set according to the RGB image and the depth image; processing the hand pose data set to obtain a 3D joint position, and taking the 3D joint position as a data set for training a software model; extracting the RGB image by a feature extractor based on a depth neural network to obtain a feature map of a hand pose; and processing the feature map according to an attention mechanism to obtain a global feature map of the hand pose.