Optimization Algorithm of Particle Filter in 3D Hand-Gesture Tracking

摘要

In HCI (Human-Computer-Interaction), 3D hand-gesture tracking is a hot research topic. In this paper, the method of particle filter is used in 3D hand-gesture tracking; we also make some improvement based on this method. Our goal is to improve the precision of 3D hand-gesture tracking. In order to achieve the goal, we optimize the sampling method and the particles' weights. We also reduce the sampling error and obtain the proper number of sampling particles. The experimental results show that the improved algorithm is better than the traditional one in tracking effect, and the time consumption is lower. Compared with the traditional random sampling method, Gauss sampling method this paper used could improve the tracking precision.