A review of 3D human pose estimation algorithms for markerless motion capture

Human pose estimation is a very active research field, stimulated by its important applications in robotics, entertainment or health and sports sciences, among others. Advances in convolutional networks triggered noticeable improvements in 2D pose estimation, leading modern 3D markerless motion capt...

Full description

Saved in:

Bibliographic Details
Published in:	Computer vision and image understanding Vol. 212; p. 103275
Main Authors:	Desmarais, Yann, Mottet, Denis, Slangen, Pierre, Montesinos, Philippe
Format:	Journal Article
Language:	English
Published:	Elsevier Inc 01.11.2021
Subjects:	3D human pose estimation Convolutional neural networks Survey Convolutional neural networks Survey 3D human pose estimation
ISSN:	1077-3142, 1090-235X
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Human pose estimation is a very active research field, stimulated by its important applications in robotics, entertainment or health and sports sciences, among others. Advances in convolutional networks triggered noticeable improvements in 2D pose estimation, leading modern 3D markerless motion capture techniques to an average error per joint of 20 mm. However, with the proliferation of methods, it is becoming increasingly difficult to make an informed choice. Here, we review the leading human pose estimation methods of the past five years, focusing on metrics, benchmarks and method structures. We propose a taxonomy based on accuracy, speed and robustness that we use to classify de methods and derive directions for future research. •Survey of recent years 3D pose estimation methods.•Analysis based on performance criteria for real-life applications.•Comparison between monocular, temporal, multi-view settings and future research propositions.
ISSN:	1077-3142 1090-235X
DOI:	10.1016/j.cviu.2021.103275