计算机应用研究2017，Vol.34Issue(2)：636-640,5.DOI:10.3969/j.issn.1001-3695.2017.02.069
基于置信度策略选择的实时目标跟踪方法
Confidence aware strategy selection based real-time object tracking
摘要
Abstract
Target tracking has always been one of the hot and difficult topics in computer vision.Due to the influences of complicated interference factors in natural scenes,the speed and accuracy of the existing target tracking methods are still to be improved.Firstly,this paper enhanced the color attribution based target tracking algorithm and made it be robust and real-time.Next,it introduced sparse collaborative appearance model to deal with the problem of error accumulation which caused drifting or even tracking failure when the object was occluded.In order to achieve fast and accurate tacking,it proposed an adaptive strategy selection mechanism to integrate the two algorithms through confidence evaluation of the tracking results.Experimental results on multiple public datasets show that,compared with the existing object tracking algorithms,the proposed method is accurate and fast.It performs well in regard of serious occlusion,illumination variation and motion blur.关键词
目标跟踪/颜色属性/协作模型/置信度策略Key words
object tracking/color attribute/collaborative model/confidence aware strategy分类
信息技术与安全科学引用本文复制引用
常德兴,陈俊周,彭强..基于置信度策略选择的实时目标跟踪方法[J].计算机应用研究,2017,34(2):636-640,5.基金项目
国家自然科学基金资助项目(61003143) （61003143）
四川省科技支撑计划资助项目(2012FZ0004) （2012FZ0004）
