一种融合Kalman预测和Mean-shift搜索的视频运动目标跟踪新方法

Approach to Tracking of Video Moving Objects by Fusing Kalman Prediction and Mean-shift Search

简要介绍Kalman滤波跟踪和Mean-shift跟踪并分析其优缺点,在此基础上提出一种融合Kalman预测和Mean-shift搜索的运动目标跟踪新方法。该方法利用Kalman滤波估计出运动目标在下一帧中最可能的出现位置,利用Mean-shift方法据此进行较小范围的搜索和目标匹配,从而可用较小的运算量获得较为可靠的跟踪效果,并适应较复杂的场景。实验结果证明了该算法的有效性。

Following a brief introduction to Kalman-filter-based tracking methods and Mean-shift-based tracking methods and a discussion about their strong points and weak points,a novel approach to tracking of video moving objects(VMOs) is proposed.By using Kalman-filter to predict locations where VMOs most probably appear in a next-frame and Mean-shift algorithm to search in the corresponding areas and match the VMOs,the approach promises to obtain more reliable tracking effect with much less computation cost.The ex...