Robust Distracter-Resistive Tracker via Learning a Multi-Component Discriminative Dictionary

Shen, W; Wu, Y; Yuan, J; Duan, L; Zhang, J; Jia, Y

Robust Distracter-Resistive Tracker via Learning a Multi-Component Discriminative Dictionary

Shen, W Wu, Y Yuan, J Duan, L Zhang, J

Jia, Y

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Circuits and Systems for Video Technology, 2019, 29 (7), pp. 2012 - 2028
Issue Date:: 2019-07-01

Closed Access

	Filename	Description	Size
	08424191.pdf	Published Version	4.4 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Shen, W	en_US
dc.contributor.author	Wu, Y	en_US
dc.contributor.author	Yuan, J	en_US
dc.contributor.author	Duan, L	en_US
dc.contributor.author	Zhang, J https://orcid.org/0000-0002-7240-3541	en_US
dc.contributor.author	Jia, Y	en_US
dc.date.issued	2019-07-01	en_US
dc.identifier.citation	IEEE Transactions on Circuits and Systems for Video Technology, 2019, 29 (7), pp. 2012 - 2028	en_US
dc.identifier.issn	1051-8215	en_US
dc.identifier.uri	http://hdl.handle.net/10453/127188
dc.description.abstract	© 1991-2012 IEEE. Discriminative dictionary learning (DDL) provides an appealing paradigm for appearance modeling in visual tracking. However, most existing DDL-based trackers cannot handle drastic appearance changes, especially for scenarios with background cluster and/or similar object interference. One reason is that they often suffer from the loss of subtle visual information, which is critical to distinguish an object from distracters. In this paper, we explore the use of activations from the convolutional layer of a convolutional neural network to improve the object representation and then propose a robust distracter-resistive tracker via learning a multi-component discriminative dictionary. The proposed method exploits both the intra-class and inter-class visual information to learn shared atoms and the class-specific atoms. By imposing several constraints into the objective function, the learned dictionary is reconstructive, compressive, and discriminative, and thus can better distinguish an object from the background. In addition, our convolutional features have structural information for object localization and balance the discriminative power and semantic information of the object. Tracking is carried out within a Bayesian inference framework where a joint decision measure is used to construct the observation model. To alleviate the drift problem, the reliable tracking results obtained online are accumulated to update the dictionary. Both the qualitative and quantitative results on the CVPR2013 benchmark, the VOT2015 data set, and the SPOT data set demonstrate that our tracker achieves substantially better overall performance against the state-of-the-art approaches.	en_US
dc.relation.ispartof	IEEE Transactions on Circuits and Systems for Video Technology	en_US
dc.relation.isbasedon	10.1109/TCSVT.2018.2862151	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Robust Distracter-Resistive Tracker via Learning a Multi-Component Discriminative Dictionary	en_US
dc.type	Journal Article
utslib.citation.volume	7	en_US
utslib.citation.volume	29	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
utslib.copyright.status	closed_access	*
pubs.issue	7	en_US
pubs.publication-status	Published	en_US
pubs.volume	29	en_US

Abstract:

© 1991-2012 IEEE. Discriminative dictionary learning (DDL) provides an appealing paradigm for appearance modeling in visual tracking. However, most existing DDL-based trackers cannot handle drastic appearance changes, especially for scenarios with background cluster and/or similar object interference. One reason is that they often suffer from the loss of subtle visual information, which is critical to distinguish an object from distracters. In this paper, we explore the use of activations from the convolutional layer of a convolutional neural network to improve the object representation and then propose a robust distracter-resistive tracker via learning a multi-component discriminative dictionary. The proposed method exploits both the intra-class and inter-class visual information to learn shared atoms and the class-specific atoms. By imposing several constraints into the objective function, the learned dictionary is reconstructive, compressive, and discriminative, and thus can better distinguish an object from the background. In addition, our convolutional features have structural information for object localization and balance the discriminative power and semantic information of the object. Tracking is carried out within a Bayesian inference framework where a joint decision measure is used to construct the observation model. To alleviate the drift problem, the reliable tracking results obtained online are accumulated to update the dictionary. Both the qualitative and quantitative results on the CVPR2013 benchmark, the VOT2015 data set, and the SPOT data set demonstrate that our tracker achieves substantially better overall performance against the state-of-the-art approaches.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/127188