CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Dynamic Collaborative Tracking
Guibo Zhu1; Zhaoxiang Zhang1,2,3; Jinqiao Wang1,2; Yi Wu4,5; Hanqing Lu1,3
Source PublicationIIEEE Transactions on Neural Networks and Learning Systems
2018
Issue0Pages:0
AbstractCorrelation 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.
KeywordCorrelation Filter Distracter Suppression Online Learning Visual Tracking
Subject AreaComputer Science, Artificial intelligence-Computer Science, Cybernetics
DOI10.1109/TNNLS.2018.2861838
Indexed BySCI
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/22068
Collection模式识别国家重点实验室_图像与视频分析
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.CAS Center for Excellence in Brain Science and Intelligence Technology
3.University of Chinese Academy of Sciences
4.Nanjing Audit University
5.Indiana University School of Medicine
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Guibo Zhu,Zhaoxiang Zhang,Jinqiao Wang,et al. Dynamic Collaborative Tracking[J]. IIEEE Transactions on Neural Networks and Learning Systems,2018(0):0.
APA Guibo Zhu,Zhaoxiang Zhang,Jinqiao Wang,Yi Wu,&Hanqing Lu.(2018).Dynamic Collaborative Tracking.IIEEE Transactions on Neural Networks and Learning Systems(0),0.
MLA Guibo Zhu,et al."Dynamic Collaborative Tracking".IIEEE Transactions on Neural Networks and Learning Systems .0(2018):0.
Files in This Item: Download All
File Name/Size DocType Version Access License
Dynamic Collaborativ(2492KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Guibo Zhu]'s Articles
[Zhaoxiang Zhang]'s Articles
[Jinqiao Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Guibo Zhu]'s Articles
[Zhaoxiang Zhang]'s Articles
[Jinqiao Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Guibo Zhu]'s Articles
[Zhaoxiang Zhang]'s Articles
[Jinqiao Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Dynamic Collaborative Tracking.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.