Abstract
Depth ambiguity is one of the main challenges of three-dimensional (3D) human pose estimation (HPE). The recent strategies of disambiguating have brought significant progress and remarkable breakthroughs in the field of 3D human pose estimation (3D HPE). This survey extensively reviews the causes and solutions of the depth ambiguity. The solutions are systematically classified into four categories: camera parameter constraints, temporal consistency constraints, kinematic constraints, and image cues constraints. This paper summarizes the performance comparison, challenges, main frameworks, and evaluation metrics, and discusses some promising future research directions.
Funder
Research on artificial intelligence cardiopulmonary resuscitation training and assessment system
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference38 articles.
1. Research progress of two-dimensional human pose estimation based on deep learning;Liu;Comput. Eng.,2021
2. A survey of two dimension pose estimation;Han;J. Xi’an Univ. Posts Telecommun.,2017
3. A review of deep learning techniques for 2D and 3D human pose estimation
4. Deep 3D human pose estimation: A review
5. VIBE: Video Inference for Human Body Pose and Shape Estimation;Kocabas;Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2020
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献