Robust Object Tracking by Nonlinear Learning
-
Altmetric Citations
Ma, Bo; Hu, Hongwei; Shen, Jianbing; Zhang, Yuping; Shao, Ling; Porikli, Fatih
Description
We propose a method that obtains a discriminative visual dictionary and a nonlinear classifier for visual tracking tasks in a sparse coding manner based on the globally linear approximation for a nonlinear learning theory. Traditional discriminative tracking methods based on sparse representation learn a dictionary in an unsupervised way and then train a classifier, which may not generate both descriptive and discriminative models for targets by treating dictionary learning and classifier...[Show more]
dc.contributor.author | Ma, Bo | |
---|---|---|
dc.contributor.author | Hu, Hongwei | |
dc.contributor.author | Shen, Jianbing | |
dc.contributor.author | Zhang, Yuping | |
dc.contributor.author | Shao, Ling | |
dc.contributor.author | Porikli, Fatih | |
dc.date.accessioned | 2019-04-17T04:45:46Z | |
dc.identifier.issn | 2162-237X | |
dc.identifier.uri | http://hdl.handle.net/1885/160398 | |
dc.description.abstract | We propose a method that obtains a discriminative visual dictionary and a nonlinear classifier for visual tracking tasks in a sparse coding manner based on the globally linear approximation for a nonlinear learning theory. Traditional discriminative tracking methods based on sparse representation learn a dictionary in an unsupervised way and then train a classifier, which may not generate both descriptive and discriminative models for targets by treating dictionary learning and classifier learning separately. In contrast, the proposed tracking approach can construct a dictionary that fully reflects the intrinsic manifold structure of visual data and introduces more discriminative ability in a unified learning framework. Finally, an iterative optimization approach, which computes the optimal dictionary, the associated sparse coding, and a classifier, is introduced. Experiments on two benchmarks show that our tracker achieves a better performance compared with some popular tracking algorithms. | |
dc.description.sponsorship | This work was supported in part by the National Natural Science Foundation of China under Grant 61472036, Grant 61272359, Grant 61672099, and Grant 81627803, in part by the National Key Research and Development Program of China under Grant 2017YFC0112000, in part by the Australian Research Council’s Discovery Projects Funding Scheme under Grant DP150104645, in part by the Fok Ying-Tong Education Foundation for Young Teachers, and in part by the Joint Building Program through the Beijing Municipal Education Commission. | |
dc.format.extent | 13 pages | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en_AU | |
dc.publisher | Institute of Electrical and Electronics Engineers | |
dc.rights | © 2017 IEEE | |
dc.source | IEEE Transactions on Neural Networks and Learning Systems | |
dc.subject | global linear approximation | |
dc.subject | local coordinate coding (LCC) | |
dc.subject | nonlinear learning | |
dc.subject | object tracking | |
dc.title | Robust Object Tracking by Nonlinear Learning | |
dc.type | Journal article | |
local.description.notes | Imported from ARIES | |
local.identifier.citationvolume | 29 | |
dcterms.dateAccepted | 2017-11-10 | |
dc.date.issued | 2018-10 | |
local.identifier.absfor | 080108 - Neural, Evolutionary and Fuzzy Computation | |
local.identifier.ariespublication | u4485658xPUB1589 | |
local.publisher.url | https://ieeexplore.ieee.org/ | |
local.type.status | Accepted Version | |
local.contributor.affiliation | Ma, Bo, Beijing Institute of Technology | |
local.contributor.affiliation | Hu, Hongwei, Beijing Lab of Intelligent Information Technology | |
local.contributor.affiliation | Shen, Jianbing, Beijing Lab of Intelligent Information Technology | |
local.contributor.affiliation | Zhang, Yuping, Beijing Lab of Intelligent Information Technology, China | |
local.contributor.affiliation | Shao, Ling, JD Artificial Intelligence Research | |
local.contributor.affiliation | Porikli, Fatih, College of Engineering and Computer Science, The Australian National University | |
dc.relation | http://purl.org/au-research/grants/arc/DP150104645 | |
local.bibliographicCitation.issue | 10 | |
local.bibliographicCitation.startpage | 4769 | |
local.bibliographicCitation.lastpage | 4781 | |
local.identifier.doi | 10.1109/TNNLS.2017.2776124 | |
local.identifier.absseo | 970108 - Expanding Knowledge in the Information and Computing Sciences | |
local.identifier.absseo | 890205 - Information Processing Services (incl. Data Entry and Capture) | |
dc.date.updated | 2019-03-12T07:29:52Z | |
local.identifier.scopusID | 2-s2.0-85039778847 | |
local.identifier.thomsonID | 000445351300018 | |
dcterms.accessRights | Open Access | |
dc.provenance | http://sherpa.mimas.ac.uk/romeo/issn/2162-237X/..."Author can archive post-print (ie final draft post-refereeing) with a 24 months embargo period" (Sherpa/Romeo as of 17/4/2019) | |
Collections | ANU Research Publications |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
tnnls17LCCT-camera.pdf | 2.46 MB | Adobe PDF |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator