计算机应用研究2017，Vol.34Issue(1)：270-274,5.DOI:10.3969/j.issn.1001-3695.2017.01.061
加权的超像素级时空上下文目标跟踪
Object tracking on weighted super pixel level spatio-temporal context
摘要
Abstract
Object tracking is a hot topic in computer vision,and the complex background of the target motion,illumination change and scale change greatly affect the accuracy of target tracking.This paper analyzed the advantages and disadvantages of some current popular tracking algorithms,and for the lack of spatio-temporal context algorithm improvements:the tracking al-gorithm of weighted super pixel level spatio-temporal context.The algorithm used the feature information of pixels to cluster the target context region,and formed a super pixel level region,and the spatial context was weighted by the similarity of the super pixel region.The experimental results show that the weighted super pixel level spatio-temporal context target tracking algorithm has better accuracy and robustness in target tracking.关键词
目标跟踪/时空上下文/超像素/自适应Key words
object tracking/spatio-temporal context/super pixel/self adaption分类
信息技术与安全科学引用本文复制引用
王淑敏,宫宁生,陈逸韬..加权的超像素级时空上下文目标跟踪[J].计算机应用研究,2017,34(1):270-274,5.基金项目
国家“973”计划资助项目（2005CB321901）；软件开发环境国家重点实验室开放课题 （）
