基于运动区域检测的运动目标跟踪算法*

针对传统基于模板匹配的运动目标跟踪算法存在着计算量大、模板漂移导致跟踪失败的问题，提出了一种基于运动区域检测的运动目标跟踪算法。该算法通过采用光流法对目标运动区域进行估计，计算出光流场区域的形心，确定待匹配图相匹配范围，再用模板框在已确定区域进行模板匹配跟踪。根据某开放实验室行人录像跟踪实验表明，本算法能够有效解决模板漂移问题，提高了跟踪实时性, 实现了视频对象目标的跟踪。

Moving object tracking algorithm based on motioning region detection

Huge computation and template drift are the defeats of traditional moving object tracking method based on template matching , which may cause tracking failure. To solve these problems, this paper presented template matching tracking algorithm based on motioning region detection. This algorithm used optical flow to estimate the moving region, found the centroid of optical flow field motion, reduced the range of tracking region, then used template matching to track the object . The results of the experiment show that the algorithm can effectively solve the problems of template drift, improve real-time of tracking and track the object in the video images.