Abstract: In order to solve the problem of inaccurate locating caused by low differentiation between object color and background color, an improved algorithm of target tracking is proposed. This algorithm, using Harris-mean shift algorithm for object search. Then according to known position information, least square method is used to predict the next position of the target. Thus target tracking is finally realized. Experiment indicates that the proposed algorithm can effectively improve the accuracy and real-time performance of the target tracking system.

Key words: target tracking, mean shift, Harris corners, least square

摘要： 为了有效地解决目标颜色与背景颜色区分度较低而引起的目标定位不准确的问题，提出了一种改进的运动目标跟踪算法。该算法利用Harris-mean shift跟踪算法进行目标搜索，然后根据目标已知位置信息采用最小二乘法得到目标在下一帧中的位置，最终实现目标跟踪。实验证明该算法能够有效地提高跟踪的准确性和实时性。

关键词: 目标跟踪, 均值漂移, Harris角点检测, 最小二乘法