Multi-View Human Body Pose Estimation with CUDA-PSO

In this paper, we formulate the body pose estimation as a multi-dimensional nonlinear optimization problem, suitable to be approximately solved by a meta-heuristic, specifically, the particle swarm optimization (PSO). Starting from multi-view video sequences acquired in a studio environment, a full skeletal configuration of the human body is retrieved. We use a generic subdivision body model in 3D to generate solutions for the optimization problem. PSO then looks for the best match between the silhouettes generated by the projection of the model in a candidate pose and the silhouettes extracted from the original video sequence. The optimization method, in this case PSO, is run in parallel on the Graphics Processing Unit (GPU) and is implemented in Cuda-C™ on the nVidia CUDA™ architecture. We compare the results obtained by different configurations of the camera setup, fitness function, and PSO neighborhood topologies.