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. Copyright © 2010 Y.-K.Wang and K.-Y. Cheng.