均值漂移框架下基于背景差分的运动目标跟踪

Moving target tracking based on background subtraction in the framework of Mean Shift

提出了一种基于背景差分法原理的均值漂移MS跟踪算法。使用距离度量函数判断目标是否失去跟踪,当MS跟踪目标位置发生较大偏移时,通过使用背景差分法提取的目标形心位置对其进行修正。实验结果表明,该方法应用于实时运动目标的跟踪时具有良好的跟踪效果。

This paper adopts an MS tracking algorithm based on background method principle. Using metric distance function determines whether a target tracking loses, when MS tracking is in great deviation of target location, it＇s position can be amended by the use of background difference method. The experimental results show that the method has good tracking effect when applying in the real-time tracking of moving targets.