Robust Visual Tracking via Appearance Modeling and Sparse Representation | |
Li, Ming; Ma, Fanglan; Nian, Fuzhong | |
刊名 | JOURNAL OF COMPUTERS |
2014-07-01 | |
卷号 | 9期号:7页码:1612-1619 |
关键词 | visual tracking appearance model sparse representation 2DPCA |
ISSN号 | 1796-203X |
DOI | 10.4304/jcp.9.7.1612-1619 |
英文摘要 | When appearance variation of object, partial occlusion or illumination change in object images occurs, most existing tracking approaches fail to track the target effectively. To deal with the problem, this paper proposed a robust visual tracking method based on appearance modeling and sparse representation. The proposed method exploits two-dimensional principal component analysis (2DPCA) with sparse representation theory for constructing appearance model. Then tracking is achieved by Bayesian inference framework, in which a particle filter is applied to evaluate the target state sequentially over time. In addition, to make the observation model more robust, the incremental learning algorithm is used to update the template set. Both qualitative and quantitative evaluations on four publicly available benchmark video sequences demonstrate that the proposed visual tracking algorithm performs better than several state-of-the-art algorithms. |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ACAD PUBL |
WOS记录号 | WOS:000218222800016 |
内容类型 | 期刊论文 |
源URL | [http://ir.lut.edu.cn/handle/2XXMBERH/155705] |
专题 | 计算机与通信学院 |
作者单位 | Lanzhou Univ Technol, Sch Comp & Commun, Lanzhou, Gansu, Peoples R China |
推荐引用方式 GB/T 7714 | Li, Ming,Ma, Fanglan,Nian, Fuzhong. Robust Visual Tracking via Appearance Modeling and Sparse Representation[J]. JOURNAL OF COMPUTERS,2014,9(7):1612-1619. |
APA | Li, Ming,Ma, Fanglan,&Nian, Fuzhong.(2014).Robust Visual Tracking via Appearance Modeling and Sparse Representation.JOURNAL OF COMPUTERS,9(7),1612-1619. |
MLA | Li, Ming,et al."Robust Visual Tracking via Appearance Modeling and Sparse Representation".JOURNAL OF COMPUTERS 9.7(2014):1612-1619. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论