A novel fitting algorithm using the ICP and the particle filters for robust 3d human body motion tracking
Dae-Hwan Kim, Daijin Kim · 2008
This paper proposes a novel fitting algorithm using the iterative closest point (ICP) registration algorithm and the particle filters for robust 3D human body motion tracking. We use the ICP registration algorithm that fits the 3D human body model to the 3D articulation data in a hierarchical manner. However, it often can not fit under the rapidly moving human body motion. To solve this problem, we combine the modified particle filter with the ICP algorithm. It can search the most appropriate motion parameters by using the observation model based on the surface normal vector and the binary valued function and the state transitional model based on the motion history information. Experimental results show that the proposed combined fitting algorithm provides accurate fitting performance and high convergence rate.