Structured and Consistent Multi-Layer Multi-Kernel Subtask Correction Filter Tracker
Fan BJ(范保杰)2; Cong Y(丛杨)1; Tang YD(唐延东)1; Tian JD(田建东)1; Xu, Chenliang3
刊名IEEE Transactions on Circuits and Systems for Video Technology
2021
卷号31期号:6页码:2328-2342
关键词Layered multi-subtask multi-kernel learning structured correction particle filter tracking temporal-spatial consistency object tracking
ISSN号1051-8215
产权排序2
英文摘要

Some multi-task correlation filter trackers achieve the top-ranked performance in terms of accuracy and robustness. However, they directly fuse multiple types of features into a single kernel space. This operation fails to fully explore the discriminative strength and diversity of different features, and also ignores the structured correspondence of different tasks. To solve these issues, we propose a structured multi-kernel subtask correlation filter tracker with temporal-spatial consistency, which enjoys the merits of both layered multi-kernel subtask learning and structured correlation filter. Specifically, we firstly assign one kernel space to each channel feature. Multi-channel features correspond to multi-kernel spaces to boost their powerful discriminability. And then, we divide the target into multi-layer patches with different sizes, and regard the correlation filter trace of each patch with one channel feature as a subtask. In the following, we incorporate globally and locally structured correlation filters into a unified multi-kernel subtask particle tracking framework. The global and local subtasks complement and enhance each other with similar motion model. The proposed tracker not only exploits the cooperation and complementarity of layered multi-kernel subtask correlation filters, but also mines the underlying geometric structure of global subtasks, and the inner spatial locality correspondences of local subtasks inside the target. This operation is achieved by dual group sparsity regularized terms with mixed-norm l_{p,q} , which decomposes the multi-kernel subtask filter matrix into two collaborative components. They correspond to the adaptive filter feature selection and outlier subtask detection, respectively. Besides, the developed tracking model maintains the temporal coherence and spatial consistency of multi-layer subtask filters via the smooth regularizer. Finally, the tracking formulation is optimized by the accelerated proximal gradient approach (APG). Encouraging analyses on six benchmark datasets, verify the favorable effectiveness and robustness of our method against state-of-the-art trackers.

资助项目Ministry of Science and Technology of China[2019YFB1310300] ; National Natural Science Foundation of China[61876092] ; State key Laboratory of Robotics[2019-O07] ; State Key Laboratory of Integrated Service Network[ISN20-08]
WOS关键词OBJECT TRACKING ; VISUAL TRACKING
WOS研究方向Engineering
语种英语
WOS记录号WOS:000658365800019
资助机构Ministry of Science and Technology of China under Grant 2019YFB1310300 ; National Natural Science Foundation of China under Grant 61876092 ; State key Laboratory of Robotics under Grant 2019-O07 ; State Key Laboratory of Integrated Service Network under Grant ISN20-08
内容类型期刊论文
源URL[http://ir.sia.cn/handle/173321/29053]  
专题沈阳自动化研究所_机器人学研究室
通讯作者Fan BJ(范保杰)
作者单位1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
2.Automation College, NJUPT, Nanjing, China
3.Department of Computer Science, University of Rochester, Rochester, NY, United States
推荐引用方式
GB/T 7714
Fan BJ,Cong Y,Tang YD,et al. Structured and Consistent Multi-Layer Multi-Kernel Subtask Correction Filter Tracker[J]. IEEE Transactions on Circuits and Systems for Video Technology,2021,31(6):2328-2342.
APA Fan BJ,Cong Y,Tang YD,Tian JD,&Xu, Chenliang.(2021).Structured and Consistent Multi-Layer Multi-Kernel Subtask Correction Filter Tracker.IEEE Transactions on Circuits and Systems for Video Technology,31(6),2328-2342.
MLA Fan BJ,et al."Structured and Consistent Multi-Layer Multi-Kernel Subtask Correction Filter Tracker".IEEE Transactions on Circuits and Systems for Video Technology 31.6(2021):2328-2342.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。


©版权所有 ©2017 CSpace - Powered by CSpace