计算机应用与软件2017，Vol.34Issue(7)：154-158,170,6.DOI:10.3969/j.issn.1000-386x.2017.07.029
基于子空间联合模型的视觉跟踪
VISUAL TRACKING BASED ON SUBSPACE COLLABORATIVE MODEL
摘要
Abstract
Target tracking is an important part of computer vision, and its robustness is always restricted to target occlusion, illumination variation and target pose change and so on.To this end, this paper proposes a visual tracking algorithm based on subspace collaborative model.In order to overcome the influence of occlusion on target tracking, this algorithm rectifies incremental subspace error by result of occlusion detection using local dynamic sparse representation.Besides, the similarity between target template and candidate template is computed based on local dynamic sparse representation.In the framework of particle filter, this algorithm is achieved based on combining incremental error with similarity.The experimental results on several sequences show that this algorithm has better performance of tracking.关键词
视觉跟踪/增量子空间/粒子滤波/联合模型/局部动态稀疏表示Key words
Visual tracking/ Incremental subspace/ Particle filter/ Collaborative model/ Local dynamic sparse representation分类
信息技术与安全科学引用本文复制引用
杨国亮,唐俊,朱松伟,王建..基于子空间联合模型的视觉跟踪[J].计算机应用与软件,2017,34(7):154-158,170,6.基金项目
国家自然科学基金项目(51365017,61305019) （51365017,61305019）
江西省科技厅青年科学基金项目(20132bab211032). （20132bab211032）
