计算机应用研究2017，Vol.34Issue(12)：3834-3838,5.DOI:10.3969/j.issn.1001-3695.2017.12.071
基于时空模型的尺度自适应视觉跟踪
Scale adaptive visual tracking based on spatio-temporal model
摘要
Abstract
Researching on the problem of low effectiveness of visual tracking with the target scale change,this paper proposed a scale adaptive visual tracking algorithm based on spatio-temporal model.Firstly,it did target feature extraction in the color naming space.Then it obtained the maximum probability of confidence map via spatio-temporal context learning.Finally,it matched the similarity of color histogram and fixed the size of tracking window with adaptive method.The experiment selected five groups of scale-change image sequences and tested in the Benchmark.The results show that the tracking success rate of STC-SA is up to 91％.STC-SA algorithm has higher tracking accuracy and real-time performance.关键词
视觉跟踪/颜色属性空间/颜色直方图/时空上下文学习/相似度匹配Key words
visual tracking/color naming space/color histogram/spatio-temporal context learning/similarity matching分类
信息技术与安全科学引用本文复制引用
刘万军,董帅含,张杰民..基于时空模型的尺度自适应视觉跟踪[J].计算机应用研究,2017,34(12):3834-3838,5.基金项目
国家自然科学基金资助项目(61172144,61401185) （61172144,61401185）
