A novel Mean Shift algorithm combined with Least Square approach and its application in target tracking

In this paper, a Mean Shift algorithm based on Least Square prediction is proposed. Based on the continuity of target´s trace, the Least Square Mean Shift (LSMS) algorithm uses the result of Least Square prediction as the initial search center of Mean Shift algorithm. Then, Mean Shift is applied to get the final target position. The computational complexity is reduced by limiting the number of iterations of Mean shift. Experimental results show that, compared with traditional Mean Shift algorithm, the proposed algorithm improves the real-time realization. Meanwhile, it has better performance on fast moving targets and non-linear moving targets.