A New Improvement on Mean-Shift Algorithm

Complex motion makes consecutive frames experience dramatic change, and thus becomes a barrier to object-tracking. Three factors contribute to more complexity of motion: longer sampling period,an moving object with complex appearance and nonrestraint movement, occlusion, which causes mean shift algorithm losing its target due to too low a Bhattacharyya coefficient. To treat it, mean shift algorithm is improved based on a new way of fast color thresholding and region merging in this paper. Visual experiments show the effectiveness of the proposed method.