Particle Swarm Optimization for Markerless Full Body Motion Capture

The estimation of full body pose is a very difficult problem in Computer Vision. Due to high dimensionality of the pose space, it is challenging to search the true body configurations for any search strategy. In this chapter, we apply the stochastic Particle Swarm Optimization (PSO) algorithm to full body pose estimation problem. Our method fits an articulated body model to the volume data reconstructed from multiple camera images. Pose estimation is performed in a hierarchical manner with space constraints enforced into each sub-optimization step. To better address the dynamic pose tracking problem, the states of swarm particles are propagated according to a weak transition model. This maintains the diversity of particles and also utilizes the temporal continuity information. 3D distance transform is used for reducing the computing time of fitness evaluations. From the experiments, we demonstrate that by using PSO, our method can robustly fit the body model of a reference pose to the beginning frame, and can track fast human movements in multiple image sequences.