3D human pose estimation in motion based on multi-stage regression
Author(s): Zhang, YT (Zhang, Yongtao); Li, S (Li, Shuang); Long, P (Long, Peng)
Source: DISPLAYS Volume: 69 Article Number: 102067 DOI: 10.1016/j.displa.2021.102067 Published: SEP 2021
Abstract: 3D human pose estimation in motion is a hot research direction in the field of computer vision. However, the performance of the algorithm is affected by the complexity of 3D spatial information, self-occlusion of human body, mapping uncertainty and other problems. In this paper, we propose a 3D human joint localization method based on multi-stage regression depth network and 2D to 3D point mapping algorithm. First of all, we use a single RGB image as the input, through the introduction of heatmap and multi-stage regression to constantly optimize the coordinates of human joint points. Then we input the 2D joint points into the mapping network for calculation, and get the coordinates of 3D human body joint points, and then to complete the 3D human body pose estimation task. The MPJPE of the algorithm in Human3.6 M dataset is 40.7. The evaluation of dataset shows that our method has obvious advantages.
Accession Number: WOS:000696991700003
ISSN: 0141-9382
eISSN: 1872-7387
Full Text: https://www.sciencedirect.com/science/article/pii/S0141938221000779?via%3Dihub