Video Tracking Using Improved Chamfer Matching and Particle Filter

Object tracking is an essential problem in the field of video and image processing. Although tracking algorithms working on gray video are convenient in actual applications, they are more difficult to be developed than those using color features, since less information is taken into account. In this paper, we proposed a novel video tracking algorithm for gray video. It uses the combination of particle filter and rotation invariant chamfer matching with a likelihood measurement which focuses on the difference. Experiment results show that the algorithm can effectively handle rotation distortion, and is stable and robust.