基于Camshift和Kalman滤波的自动跟踪算法  

An effective automatic tracking algorithm based on Camshift and Kalman filter

作　　者：梁娟[1] 项俊[1] 侯建华[1] 

机构地区：[1]中南民族大学电子信息工程学院,湖北武汉430074

出　　处：《微型机与应用》2011年第24期28-31,共4页Microcomputer & Its Applications

摘　　要：针对传统的Camshift算法在跟踪时需要手动定位目标,在颜色干扰、遮挡等复杂背景中容易跟丢目标的问题,提出了一种基于Camshift和Kalman滤波的自动跟踪算法。首先利用帧间差分法和Canny边缘检测法分割出运动目标的完整区域,然后用提取出的目标区域初始化Camshift算法的初始搜索窗口,从而实现了目标的自动跟踪。当背景中存在相似颜色干扰或者目标被严重遮挡时,采用Kalman滤波与Camshift算法相结合的改进算法进行跟踪。实验结果表明,本文改进算法在目标被严重遮挡、颜色干扰等情况下仍能有效、稳健地跟踪。An automatic tracking algorithm based on Camshift and Kalman filter is proposed in this paper to deal with the problems in traditional Camshift algorithm, such as artificial orientation and tracking failure under color interference or occlusion. The inter-frame difference and canny edge detection are combined to segment perfect moving object region accurately. Then, the initial search window for Camshift tracking algorithm is initialized by the extraction of the moving object and the moving object automatic tracking is realized. With regard to tracking under color interference or severe occlusion, an improved algorithm combined Kalman filter and Camshift is used to track the object. The experiment results demonstrate that the proposed algorithm can track the target object accurately and has better robustness to color noises and occlusion.

关 键 词：目标跟踪 CAMSHIFT算法 KALMAN滤波 帧间差分法 CANNY边缘检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]