中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 紫东太初大模型研究中心
  5. 图像与视频分析团队
Dynamic Collaborative Tracking

文献类型：期刊论文

作者Zhu, Guibo1; Zhang, Zhaoxiang1,2,3; Wang, Jinqiao3,4; Wu, Yi5,6; Lu, Hanqing3,4
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
出版日期2019-10-01
卷号30期号:10页码:3035-3046
关键词Correlation filter (CF) distracter suppression online learning visual tracking
ISSN号2162-237X
DOI10.1109/TNNLS.2018.2861838
通讯作者Zhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn)
英文摘要Correlation filter has been demonstrated remarkable success for visual tracking recently. However, most existing methods often face model drift caused by several factors, such as unlimited boundary effect, heavy occlusion, fast motion, and distracter perturbation. To address the issue, this paper proposes a unified dynamic collaborative tracking framework that can perform more flexible and robust position prediction. Specifically, the framework learns the object appearance model by jointly training the objective function with three components: target regression submodule, distracter suppression submodule, and maximum margin relation submodule. The first submodule mainly takes advantage of the circulant structure of training samples to obtain the distinguishing ability between the target and its surrounding background. The second submodule optimizes the label response of the possible distracting region close to zero for reducing the peak value of the confidence map in the distracting region. Inspired by the structure output support vector machines, the third submodule is introduced to utilize the differences between target appearance representation and distracter appearance representation in the discriminative mapping space for alleviating the disturbance of the most possible hard negative samples. In addition, a CUR filter as an assistant detector is embedded to provide effective object candidates for alleviating the model drift problem. Comprehensive experimental results show that the proposed approach achieves the state-of-the-art performance in several public benchmark data sets.
WOS关键词ROBUST VISUAL TRACKING ; ONLINE OBJECT TRACKING ; SPARSE-REPRESENTATION ; IMAGE CLASSIFICATION ; LOW-RANK ; OCCLUSION ; FEATURES ; FILTER
资助项目National Key Research and Development Program of China[2018YFB1004600] ; National Natural Science Foundation of China[61702510] ; National Natural Science Foundation of China[61773375] ; National Natural Science Foundation of China[61375036] ; National Natural Science Foundation of China[61602481] ; National Natural Science Foundation of China[61370036] ; National Natural Science Foundation of China[61772277] ; National Natural Science Foundation of China[61772527] ; Microsoft Collaborative Research Project
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000487199000013
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Microsoft Collaborative Research Project
源URL[http://ir.ia.ac.cn/handle/173211/22068]  
专题自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者Zhang, Zhaoxiang
作者单位1.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
2.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 200031, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
5.Nanjing Audit Univ, Sch Technol, Nanjing 211815, Jiangsu, Peoples R China
6.Indiana Univ Sch Med, Dept Med, Indianapolis, IN 46202 USA
推荐引用方式
GB/T 7714		 Zhu, Guibo,Zhang, Zhaoxiang,Wang, Jinqiao,et al. Dynamic Collaborative Tracking[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2019,30(10):3035-3046.
APA Zhu, Guibo,Zhang, Zhaoxiang,Wang, Jinqiao,Wu, Yi,&Lu, Hanqing.(2019).Dynamic Collaborative Tracking.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,30(10),3035-3046.
MLA Zhu, Guibo,et al."Dynamic Collaborative Tracking".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 30.10(2019):3035-3046.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。