Computer Engineering and Applications ›› 2021, Vol. 57 ›› Issue (14): 148-157.DOI: 10.3778/j.issn.1002-8331.2004-0078

Previous Articles     Next Articles

Multi-scale High-Resolution Preserving and Perspective-Invariant Hand Pose Estimation

XIONG Jie, PENG Jun, YANG Wenji, HUANG Lifang   

  1. 1.School of Computer and Information Engineering, Jiangxi Agricultural University, Nanchang 330045, China
    2.School of Software, Jiangxi Agricultural University, Nanchang 330045, China
    3.State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou 310058, China
    4.Jiangling Holdings Limited, Nanchang 330052, China
  • Online:2021-07-15 Published:2021-07-14



  1. 1.江西农业大学 计算机与信息工程学院,南昌 330045
    2.江西农业大学 软件学院,南昌 330045
    3.浙江大学 CAD&CG国家重点实验室,杭州 310058
    4.江铃控股有限公司,南昌 330052


At present, most of the networks used for 2D keypoint heatmaps estimation of hand pose use the convolutional pose machines or Hourglass network, but these two networks cannot simultaneously satisfy the requirements of high-resolution representation preserving learning and multi-scale feature fusion. In response to this problem, a multi-scale high-resolution preserving network is used, which adopts the structure of high-resolution and low-resolution representation in parallel design, and enhances the features of each resolution through the fusion of all resolution representations, and has multiple stages to extract high quality features for 2D heatmaps estimation. In order to obtain the 3D hand pose, a global rotation perspective-invariant method is also used to map the 2D heatmaps to the 3D pose. Experiments on 2D hand pose estimation and 3D hand pose estimation are conducted on three public datasets(RHD, STB, Dexter+Object), and the results verify the effectiveness of the method in hand pose estimation.

Key words: hand pose estimation, high-resolution representation, multi-scale fusion, perspective-invariant, deep learning



关键词: 手姿态估计, 高分辨率表示, 多尺度融合, 视角不变, 深度学习