Real-time multiview human pose tracking using graphics processing unit-accelerated particle swarm optimization

摘要

This paper describes how to achieve real-time tracking of 3D human motion using multiview images andrngraphics processing unit (GPU)-accelerated particle swarm optimization. The tracking involves configuringrnthe 3D human model in the pose described by each particle and then rasterizing it in each 2D plane.rnThe Compute Unified Device Architecture threads rasterize the columns of the triangles and perform thernsumming of the fitness values of pixels belonging to the processed columns. Such a parallel particle swarmrnoptimization (PSO) exhibits the level of parallelism that allows us to effectively utilize the GPU resources.rnImage acquisition and image processing are multithreaded and run on CPU in parallel with PSO-basedrnsearching for the best pose. Owing to such task decomposition, the tracking of the full human body can bernperformed at rates of 12 frames per second. For a PSO consisting of 1000 particles and executing 10 iterations,rnthe GPU achieves an average speedup of 12 over the CPU. Using marker-less motion capture systemrnconsisting of four calibrated and synchronized cameras, the efficiency comparisons were conducted on fourrnCPU cores and four GTX GPUs on two cards.