基于NCC匹配的Camshift目标跟踪算法

Camshift Target Tracking Algorithm Based on NCC Matching

目标跟踪一直以来都是机器视觉的热点问题,通常目标跟踪主要是通过寻找上下帧的相似特征来确定目标位置。Camshift算法在目标跟踪过程中一般利用的是目标的颜色信息,但在目标受到类似颜色干扰时容易跟踪失败,而NCC算法能够利用目标的结构特征。提出了一种结合Camshift与NCC的跟踪算法,使用Camshift对目标位置进行定位,同时在定位区域利用缩放比例进行NCC匹配得到目标的最终位置。实验结果表明该算法是可行有效的,对比当前传统跟踪算法其跟踪性能有着显著的提高。

Target tracking is always a hot topic of machine vision,usually target tracking determines the position of target by searching the similarity of upper and lower frames. Camshift algorithm commonly utilizes the color information of the target in the target tracking process,but the target tracking is easily failed when exists interference of similar color. While the NCC algorithm can use the structure features of target. Therefore,a tracking algorithm which combines Camshift with NCC is proposed,in which Camshift is used to locate the positioning of target,meantime,NCC matching is conducted by using the scaling in location area,then the final position of target is obtained. The experimental results show that the algorithm is feasible and effective,and the tracking performance is improved significantly compared with the traditional tracking algorithm.