National University of Defense Technology

Yixiang He

Jie Jiang

Yingmei Wei

Lai Kang

Yuxiang Xie

Yang Liu

Liang Bai

Xianghan Wang

Junyan Yang

Jiahao Sun

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.

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

Growing community of inventors

Hunan, China

Yixiang He