Open Access
REVIEW
Overview of 3D Human Pose Estimation
Jianchu Lin1,2, Shuang Li3, Hong Qin3,4, Hongchang Wang3, Ning Cui6, Qian Jiang7, Haifang Jian3,*, Gongming Wang5,*
1
Huaiyin Institute of Technology, Huai’an, 223000, China
2
Jiangsu Outlook Shenzhou Big Data Technology Co., Ltd., Nanjing, 210002, China
3
Institute of Semiconductors, Chinese Academy of Sciences, Beijing, 100083, China
4
Center of Materials Science and Optoelectronics Engineering & School of Integrated Circuits, University of Chinese Academy of
Sciences, Beijing, 100049, China
5
Inspur Software Group Company, Ltd., Jinan, 250104, China
6
China Great Wall Industry Corporation, Beijing, 100054, China
7
China Great Wall Industry Corporation Navigation Co., Ltd., Beijing, 100144, China
* Corresponding Authors: Haifang Jian. Email: ; Gongming Wang. Email:
(This article belongs to the Special Issue: Enabled and Human-centric Computational Intelligence Solutions for Visual Understanding and Application)
Computer Modeling in Engineering & Sciences 2023, 134(3), 1621-1651. https://doi.org/10.32604/cmes.2022.020857
Received 16 December 2021; Accepted 26 April 2022; Issue published 20 September 2022
Abstract
3D human pose estimation is a major focus area in the field of computer vision, which plays an important role
in practical applications. This article summarizes the framework and research progress related to the estimation of
monocular RGB images and videos. An overall perspective of methods integrated with deep learning is introduced.
Novel image-based and video-based inputs are proposed as the analysis framework. From this viewpoint, common
problems are discussed. The diversity of human postures usually leads to problems such as occlusion and ambiguity,
and the lack of training datasets often results in poor generalization ability of the model. Regression methods are
crucial for solving such problems. Considering image-based input, the multi-view method is commonly used to
solve occlusion problems. Here, the multi-view method is analyzed comprehensively. By referring to video-based
input, the human prior knowledge of restricted motion is used to predict human postures. In addition, structural
constraints are widely used as prior knowledge. Furthermore, weakly supervised learning methods are studied and
discussed for these two types of inputs to improve the model generalization ability. The problem of insufficient
training datasets must also be considered, especially because 3D datasets are usually biased and limited. Finally,
emerging and popular datasets and evaluation indicators are discussed. The characteristics of the datasets and the
relationships of the indicators are explained and highlighted. Thus, this article can be useful and instructive for
researchers who are lacking in experience and find this field confusing. In addition, by providing an overview of
3D human pose estimation, this article sorts and refines recent studies on 3D human pose estimation. It describes
kernel problems and common useful methods, and discusses the scope for further research.
Keywords
Cite This Article
APA Style
Lin, J., Li, S., Qin, H., Wang, H., Cui, N. et al. (2023). Overview of 3D human pose estimation. Computer Modeling in Engineering & Sciences, 134(3), 1621-1651. https://doi.org/10.32604/cmes.2022.020857
Vancouver Style
Lin J, Li S, Qin H, Wang H, Cui N, Jiang Q, et al. Overview of 3D human pose estimation. Comput Model Eng Sci. 2023;134(3):1621-1651 https://doi.org/10.32604/cmes.2022.020857
IEEE Style
J. Lin et al., "Overview of 3D Human Pose Estimation," Comput. Model. Eng. Sci., vol. 134, no. 3, pp. 1621-1651. 2023. https://doi.org/10.32604/cmes.2022.020857