Knowledge Commons of Institute of Automation,CAS
Robust Visual Tracking via Exclusive Context Modeling | |
Zhang, Tianzhu1,2; Ghanem, Bernard1,3; Liu, Si4; Xu, Changsheng2; Ahuja, Narendra5 | |
发表期刊 | IEEE TRANSACTIONS ON CYBERNETICS |
2016 | |
卷号 | 46期号:1页码:51-63 |
文章类型 | Article |
摘要 | In this paper, we formulate particle filter-based object tracking as an exclusive sparse learning problem that exploits contextual information. To achieve this goal, we propose the context-aware exclusive sparse tracker (CEST) to model particle appearances as linear combinations of dictionary templates that are updated dynamically. Learning the representation of each particle is formulated as an exclusive sparse representation problem, where the overall dictionary is composed of multiple group dictionaries that can contain contextual information. With context, CEST is less prone to tracker drift. Interestingly, we show that the popular L-1 tracker [1] is a special case of our CEST formulation. The proposed learning problem is efficiently solved using an accelerated proximal gradient method that yields a sequence of closed form updates. To make the tracker much faster, we reduce the number of learning problems to be solved by using the dual problem to quickly and systematically rank and prune particles in each frame. We test our CEST tracker on challenging benchmark sequences that involve heavy occlusion, drastic illumination changes, and large pose variations. Experimental results show that CEST consistently outperforms state-of-the-art trackers. |
关键词 | Contextual Information Exclusive Sparse Learning Particle Filter Tracking |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1109/TCYB.2015.2393307 |
关键词[WOS] | OBJECT TRACKING ; OCCLUSION DETECTION |
收录类别 | SCI |
语种 | 英语 |
项目资助者 | Advanced Digital Sciences Center, Singapore's Agency for Science, Technology and Research, under a Research Grant for the Human Sixth Sense Programme ; National Program on Key Basic Research Project (973 Program)(2012CB316304) ; National Natural Science Foundation of China(61225009) |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Cybernetics |
WOS记录号 | WOS:000367144300006 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/10648 |
专题 | 多模态人工智能系统全国重点实验室_多媒体计算 |
作者单位 | 1.Adv Digital Sci Ctr, Singapore 138632, Singapore 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.King Abdullah Univ Sci & Technol, Thuwal 239556900, Saudi Arabia 4.Chinese Acad Sci, Inst Informat Engn, Beijing 100190, Peoples R China 5.Univ Illinois, Beckman Inst, Dept Elect & Comp Engn, Coordinated Sci Lab, Urbana, IL 61801 USA |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhang, Tianzhu,Ghanem, Bernard,Liu, Si,et al. Robust Visual Tracking via Exclusive Context Modeling[J]. IEEE TRANSACTIONS ON CYBERNETICS,2016,46(1):51-63. |
APA | Zhang, Tianzhu,Ghanem, Bernard,Liu, Si,Xu, Changsheng,&Ahuja, Narendra.(2016).Robust Visual Tracking via Exclusive Context Modeling.IEEE TRANSACTIONS ON CYBERNETICS,46(1),51-63. |
MLA | Zhang, Tianzhu,et al."Robust Visual Tracking via Exclusive Context Modeling".IEEE TRANSACTIONS ON CYBERNETICS 46.1(2016):51-63. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
TCYB15_Exclusive Con(1451KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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