Skip to main content

A Two-Stage Bayesian Network Method for 3D Human Pose Estimation from Monocular Image Sequences

Abstract

This paper proposes a novel human motion capture method that locates human body joint position and reconstructs the human pose in 3D space from monocular images. We propose a two-stage framework including 2D and 3D probabilistic graphical models which can solve the occlusion problem for the estimation of human joint positions. The 2D and 3D models adopt directed acyclic structure to avoid error propagation of inference. Image observations corresponding to shape and appearance features of humans are considered as evidence for the inference of 2D joint positions in the 2D model. Both the 2D and 3D models utilize the Expectation Maximization algorithm to learn prior distributions of the models. An annealed Gibbs sampling method is proposed for the two-stage method to inference the maximum posteriori distributions of joint positions. The annealing process can efficiently explore the mode of distributions and find solutions in high-dimensional space. Experiments are conducted on the HumanEva dataset with image sequences of walking motion, which has challenges of occlusion and loss of image observations. Experimental results show that the proposed two-stage approach can efficiently estimate more accurate human poses.

Publisher note

To access the full article, please see PDF.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Yuan-Kai Wang.

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License (https://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and Permissions

About this article

Cite this article

Wang, YK., Cheng, KY. A Two-Stage Bayesian Network Method for 3D Human Pose Estimation from Monocular Image Sequences. EURASIP J. Adv. Signal Process. 2010, 761460 (2010). https://doi.org/10.1155/2010/761460

Download citation

Keywords

  • Joint Position
  • Expectation Maximization Algorithm
  • Image Observation
  • Probabilistic Graphical Model
  • Monocular Image