期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2016
卷号：9
期号：11
页码：371-382
出版社：SERSC
摘要：To improve the robustness of object tracking method, the study on tracking method based on sparse representation is done in the paper, and a new object tracking method based on hybrid templates is proposed. The sparse representation of global template to candidate target generatesreconstruct error, and the sparse representation of local structural sparse dictionary to candidate target generatessimilarity function. The optimal discriminate result of the logistic decision function which combine two models regard as tracking result, the experimental results and analysis demonstrate the performance of the proposed method.
关键词：Object tracking; Sparse representation; Logistic decision function ;Hybrid ;templates
