Show simple item record

dc.contributor.authorZheng, F
dc.contributor.authorShao, L
dc.contributor.authorBrownjohn, J
dc.contributor.authorRacic, V
dc.date.accessioned2016-04-22T12:38:03Z
dc.date.issued2014-09
dc.description.abstractIn this paper, a Learn++ (LPP) tracker is proposed to efficiently select specific classifiers for robust and long-term object tracking. In contrast to previous online methods, LPP tracker dynamically maintains a set of basic classifiers which are trained sequentially without accessing original data but preserving the previously acquired knowledge. The different subsets of basic classifiers can be specified to solve different sub-problems occurred in a non-stationary environment. Thus, an optimal classifier can be approximated in an active subspace spanned by selected adaptive basic classifiers. As a result, LPP tracker can address the "concept drift", by automatically adjusting the active subset and searching the optimal classifier in an active subspace spanned by the subset according to the distribution of the samples and recent performance. Experimental results show that LPP tracker yields state-of-the-art performance under various challenging environmental conditions and, especially, can overcome several challenges simultaneously.en_GB
dc.identifier.citationBMVC 2014 - Proceedings of the British Machine Vision Conference 2014en_GB
dc.identifier.urihttp://hdl.handle.net/10871/21193
dc.language.isoenen_GB
dc.publisherBritish Machine Vision Conferenceen_GB
dc.relation.urlhttp://bmvc2014.cs.nott.ac.uk/en_GB
dc.rights© 2014. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.en_GB
dc.titleLearn++ for robust object trackingen_GB
dc.typeConference paperen_GB
dc.date.available2016-04-22T12:38:03Z
dc.descriptionBMVC 2014 - British Machine Vision Conference 2014, 1-5 September 2014, University of Nottingham, UKen_GB


Files in this item

This item appears in the following Collection(s)

Show simple item record