Robust Visual Tracking via Structured Multi-Task Sparse Learning | |
Tianzhu Zhang1![]() | |
刊名 | International Journal of Computer Vision
![]() |
2013 | |
卷号 | 101期号:2页码:367-383 |
关键词 | Visual Tracking Particle Filter Graph Structure Sparse Representation Multi-task Learning |
DOI | 10.1007/s11263-012-0582-z |
文献子类 | 期刊 |
英文摘要 | In this paper, we formulate object tracking in a particle filter framework as a structured multi-task sparse learning problem, which we denote as Structured Multi-Task Tracking (S-MTT). Since we model particles as linear combinations of dictionary templates that are updated dynamically, learning the representation of each particle is considered a single task in Multi-Task Tracking (MTT). By employing popular sparsity-inducing mixed norms and we regularize the representation problem to enforce joint sparsity and learn the particle representations together. As compared to previous methods that handle particles independently, our results demonstrate that mining the interdependencies between particles improves tracking performance and overall computational complexity. Interestingly, we show that the popular tracker (Mei and Ling, IEEE Trans Pattern Anal Mach Intel 33(11):2259-2272, 2011) is a special case of our MTT formulation (denoted as the tracker) when Under the MTT framework, some of the tasks (particle representations) are often more closely related and more likely to share common relevant covariates than other tasks. Therefore, we extend the MTT framework to take into account pairwise structural correlations between particles (e.g. spatial smoothness of representation) and denote the novel framework as S-MTT. The problem of learning the regularized sparse representation in MTT and S-MTT can be solved efficiently using an Accelerated Proximal Gradient (APG) method that yields a sequence of closed form updates. As such, S-MTT and MTT are computationally attractive. We test our proposed approach on challenging sequences involving heavy occlusion, drastic illumination changes, and large pose variations. Experimental results show that S-MTT is much better than MTT, and both methods consistently outperform state-of-the-art trackers. |
学科主题 | Computer Science |
URL标识 | 查看原文 |
资助项目 | Advanced Digital Sciences Center from Singapore's Agency for Science, Technology and Research (A*STAR) |
WOS关键词 | OBJECT TRACKING ; PARTICLE FILTER ; EIGENTRACKING ; MODELS |
WOS研究方向 | Computer Science |
语种 | 英语 |
WOS记录号 | WOS:000314291600008 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/13643] ![]() |
专题 | 自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队 |
通讯作者 | Si Liu |
作者单位 | 1.Advanced Digital Sciences Center, Singapore 2.King Abdullah University of Science and Technology 3.National University of Singapore 4.University of Illinois at Urbana-Champaign |
推荐引用方式 GB/T 7714 | Tianzhu Zhang,Bernard Ghanem,Si Liu,et al. Robust Visual Tracking via Structured Multi-Task Sparse Learning[J]. International Journal of Computer Vision,2013,101(2):367-383. |
APA | Tianzhu Zhang,Bernard Ghanem,Si Liu,&Narendra Ahuja.(2013).Robust Visual Tracking via Structured Multi-Task Sparse Learning.International Journal of Computer Vision,101(2),367-383. |
MLA | Tianzhu Zhang,et al."Robust Visual Tracking via Structured Multi-Task Sparse Learning".International Journal of Computer Vision 101.2(2013):367-383. |
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