Robust Visual Tracking by Exploiting the Historical Tracker Snapshots

Li, J; Hong, Z; Zhao, B

Robust Visual Tracking by Exploiting the Historical Tracker Snapshots

Li, J Hong, Z Zhao, B

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings of the IEEE International Conference on Computer Vision, 2016, 2016-February pp. 604 - 612
Issue Date:: 2016-02-11

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download full textAdobe PDF (1.34 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Li, J	en_US
dc.contributor.author	Hong, Z	en_US
dc.contributor.author	Zhao, B	en_US
dc.date.issued	2016-02-11	en_US
dc.identifier.citation	Proceedings of the IEEE International Conference on Computer Vision, 2016, 2016-February pp. 604 - 612	en_US
dc.identifier.isbn	9781467383905	en_US
dc.identifier.issn	1550-5499	en_US
dc.identifier.uri	http://hdl.handle.net/10453/41899
dc.description.abstract	© 2015 IEEE. Variations of target appearances due to illumination changes, heavy occlusions and abrupt motions are the major factors for tracking failures. In this paper, we show that these failures can be effectively handled by exploiting the trajectory consistency between the current tracker and its historical trained snapshots. Here, we propose a Scale-adaptive Multi-Expert (SME) tracker, which combines the current tracker and its historical trained snapshots to construct a multi-expert ensemble. The best expert in the ensemble is then selected according to the accumulated trajectory consistency criteria. The base tracker estimates the translation accurately with regression based correlation filter, and an effective scale adaptive scheme is introduced to handle scale changes on-the-fly. SME is extensively evaluated on the 51 sequences tracking benchmark and VOT2015 dataset. The experimental results demonstrate the excellent performance of the proposed approach against state-of-the-art methods with real-time speed.	en_US
dc.relation.ispartof	Proceedings of the IEEE International Conference on Computer Vision	en_US
dc.relation.isbasedon	10.1109/ICCVW.2015.82	en_US
dc.title	Robust Visual Tracking by Exploiting the Historical Tracker Snapshots	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2016-February	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/Students
utslib.copyright.status	open_access
pubs.publication-status	Published	en_US
pubs.volume	2016-February	en_US

Abstract:

© 2015 IEEE. Variations of target appearances due to illumination changes, heavy occlusions and abrupt motions are the major factors for tracking failures. In this paper, we show that these failures can be effectively handled by exploiting the trajectory consistency between the current tracker and its historical trained snapshots. Here, we propose a Scale-adaptive Multi-Expert (SME) tracker, which combines the current tracker and its historical trained snapshots to construct a multi-expert ensemble. The best expert in the ensemble is then selected according to the accumulated trajectory consistency criteria. The base tracker estimates the translation accurately with regression based correlation filter, and an effective scale adaptive scheme is introduced to handle scale changes on-the-fly. SME is extensively evaluated on the 51 sequences tracking benchmark and VOT2015 dataset. The experimental results demonstrate the excellent performance of the proposed approach against state-of-the-art methods with real-time speed.

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

http://hdl.handle.net/10453/41899