SIA OpenIR  > 机器人学研究室
Discriminative multi-task objects tracking with active feature selection and drift correction
Fan BJ(范保杰); Cong Y(丛杨); Du YK(杜英魁)
Department机器人学研究室
Source PublicationPattern Recognition
ISSN0031-3203
2014
Volume47Issue:12Pages:3828–3840
Indexed BySCI ; EI
EI Accession number20143600016923
WOS IDWOS:000342870900008
Contribution Rank2
KeywordMonte Carlo Methods Signal Filtering And Prediction
AbstractIn this paper, we propose a discriminative multi-task objects tracking method with active feature selection and drift correction. The developed method formulates object tracking in a particle filter framework as multi-Task discriminative tracking. As opposed to generative methods that handle particles separately, the proposed method learns the representation of all the particles jointly and the corresponding coefficients are similar. The tracking algorithm starts from the active feature selection scheme, which adaptively chooses suitable number of discriminative features from the tracked target and background in the dynamic environment. Based on the selected feature space, the discriminative dictionary is constructed and updated dynamically. Only a few of them are used to represent all the particles at each frame. In other words, all the particles share the same dictionary templates and their representations are obtained jointly by discriminative multi-task learning. The particle that has the highest similarity with the dictionary templates is selected as the next tracked target state. This jointly sparsity and discriminative learning can exploit the relationship between particles and improve tracking performance. To alleviate the visual drift problem encountered in object tracking, a two-stage particle filtering algorithm is proposed to complete drift correction and exploit both the ground truth information of the first frame and observations obtained online from the current frame. Experimental evaluations on challenging sequences demonstrate the effectiveness, accuracy and robustness of the proposed tracker in comparison with state-of-the-art algorithms. © 2014 Elsevier Ltd.
Language英语
WOS HeadingsScience & Technology ; Technology
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS KeywordVISUAL TRACKING ; MODEL
WOS Research AreaComputer Science ; Engineering
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/15121
Collection机器人学研究室
Corresponding AuthorFan BJ(范保杰)
Affiliation1.College of Automation, Nanjing University of Posts and Telecommunications, No.9 Wenyuan Road, Nanjing, China
2.State Key Laboratory of Robotics, Shenyang Institute Automation, Chinese Academy of Sciences, Shenyang, China
Recommended Citation
GB/T 7714
Fan BJ,Cong Y,Du YK. Discriminative multi-task objects tracking with active feature selection and drift correction[J]. Pattern Recognition,2014,47(12):3828–3840.
APA Fan BJ,Cong Y,&Du YK.(2014).Discriminative multi-task objects tracking with active feature selection and drift correction.Pattern Recognition,47(12),3828–3840.
MLA Fan BJ,et al."Discriminative multi-task objects tracking with active feature selection and drift correction".Pattern Recognition 47.12(2014):3828–3840.
Files in This Item: Download All
File Name/Size DocType Version Access License
Discriminative multi(4584KB)期刊论文作者接受稿开放获取ODC PDDLView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Fan BJ(范保杰)]'s Articles
[Cong Y(丛杨)]'s Articles
[Du YK(杜英魁)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Fan BJ(范保杰)]'s Articles
[Cong Y(丛杨)]'s Articles
[Du YK(杜英魁)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Fan BJ(范保杰)]'s Articles
[Cong Y(丛杨)]'s Articles
[Du YK(杜英魁)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Discriminative multi-task objects tracking with active feature selection and drift correction.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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