CASIA OpenIR  > 智能感知与计算研究中心
Severely Blurred Object Tracking by Learning Deep Image Representations
Ding, Jianwei1; Huang, Yongzhen3; Liu, Wei2; Huang, Kaiqi3
Source PublicationIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
2016-02-01
Volume26Issue:2Pages:319-331
SubtypeArticle
AbstractAn implicit assumption in many generic object trackers is that the videos are blur free. However, motion blur is very common in real videos. The performance of a generic object tracker may drop significantly when it is applied to videos with severe motion blur. In this paper, we propose a new Tracking-Learning-Data approach to transfer a generic object tracker to a blur-invariant object tracker without deblurring image sequences. Before object tracking, a large set of unlabeled images is used to learn objects' visual prior knowledge, which is then transferred to the appearance model of a specific target. During object tracking, online training samples are collected from the tracking results and the context information. Different blur kernels are involved with the training samples to increase the robustness of the appearance model to severe blur, and the motion parameters of the object are estimated in the particle filter framework. Extensive experimental results demonstrate that the proposed algorithm can robustly track objects not only in severely blurred videos but also in other challenging scenes.
KeywordDeep Learning Object Tracking Severe Blur
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TCSVT.2015.2406231
Indexed BySCI
Language英语
Funding OrganizationFundamental Research Funds for Central Universities(2014JKF01116) ; National High Technology Research and Development Program of China(2013AA014604) ; National Natural Science Foundation of China(61402484 ; SAMSUNG Global Research Outreach Program ; CCF-Tencent Program ; 360 OpenLab Program ; 61203252)
WOS Research AreaEngineering
WOS SubjectEngineering, Electrical & Electronic
WOS IDWOS:000370935900005
Citation statistics
Cited Times:12[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/11356
Collection智能感知与计算研究中心
Affiliation1.Peoples Publ Secur Univ China, Beijing 430072, Peoples R China
2.Nanyang Normal Univ, Nanyang 450001, Henan, Peoples R China
3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Ding, Jianwei,Huang, Yongzhen,Liu, Wei,et al. Severely Blurred Object Tracking by Learning Deep Image Representations[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2016,26(2):319-331.
APA Ding, Jianwei,Huang, Yongzhen,Liu, Wei,&Huang, Kaiqi.(2016).Severely Blurred Object Tracking by Learning Deep Image Representations.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,26(2),319-331.
MLA Ding, Jianwei,et al."Severely Blurred Object Tracking by Learning Deep Image Representations".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 26.2(2016):319-331.
Files in This Item: Download All
File Name/Size DocType Version Access License
dingjianwei-2016-.pd(3657KB)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
[Ding, Jianwei]'s Articles
[Huang, Yongzhen]'s Articles
[Liu, Wei]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ding, Jianwei]'s Articles
[Huang, Yongzhen]'s Articles
[Liu, Wei]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ding, Jianwei]'s Articles
[Huang, Yongzhen]'s Articles
[Liu, Wei]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: dingjianwei-2016-.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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