基于Mean Shift的多模板目标跟踪算法  

Multiple template moving object tracking based on Mean Shift

作　　者：丁晓凤[1] 尚振宏[1] 刘辉[1] 陈熙[1] DING Xiaofeng;SHANG Zhenhong;LIU Hui;CHEN Xi(College of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China)

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650500

出　　处：《计算机工程与应用》2017年第6期141-144,173,共5页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61462052;No.31300938;No.61262040)

摘　　要：目标跟踪是计算机视觉研究领域的热点之一,并得到广泛应用。其中基于Mean Shift的运动目标跟踪算法因其计算量小,实时性好,简单易行等特点而受到广泛关注,但该算法在目标突变或严重帧丢失以及目标严重遮挡的情况跟踪效果不佳,留下了改进空间。在传统基于Mean Shift运动目标跟踪方法基础上,通过创建并维护多样性模板库为跟踪过程提供更丰富的目标描述信息,提高算法运动目标跟踪效果。实验结果表明,新算法较好地解决了在目标突变和严重帧丢失情况下不能准确跟踪目标的问题,并且对目标的完全遮挡也具有很好的鲁棒性。Object tracking is one of the hot topics in computer vision. Although object tracking algorithms based on Mean Shift gain a lot of attention because of small calculation, real-time tracking and simple procedure, it can not deal well with the conditions of severe object mutation, frame loss or severe occlusion, which is needed to be improved. Different from the traditional moving object tracking method based on Mean Shift, this paper creates and maintains a diverse of template library providing more abundant description information to improve the tacking performance. Experimental results show that the new algorithm can track the moving object better in above situations, even keep a good robustness when complete object occlusion takes place.

关 键 词：运动目标跟踪 MEANSHIFT 多模板 模板库 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]