Robust object tracking via inertial potential based mean shift
Xin Sun, Hongxun Yao, Shengping Zhang · 2011
We present a novel mean shift approach in this paper for robust object tracking based on an inertial potential model. Conventional mean shift based trackers exploit only appearance information of observation to determine the target location which usually cannot effectively distinguish the foreground from background in complex scenes. In contrast, by constructing the inertial potential model, the proposed algorithm makes good use of motion information of previous frames adaptively to track the target. Then the probability of all candidates is modeled by considering both the photometric and motion cues in a Bayesian manner, leading the mean shift vector finally converge to the location with maximum likelihood of being the target. Experimental results on several challenging video sequences have verified that the proposed method is compared very robust and effective with the traditional mean shift based trackers in many complicated scenes.