Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/77318
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Robust tracking with weighted online structured learning
Author: Yao, R.
Shi, Q.
Shen, C.
Zhang, Y.
Van Den Hengel, A.
Citation: Proceedings of the 12th European Conference on Computer Vision, held in Florence, Italy, 7-13 October, 2012 / A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato and C. Schmid (eds.): pp.158-172
Publisher: Springer-Verlag
Publisher Place: Germany
Issue Date: 2012
Series/Report no.: Lecture Notes in Computer Science; 7574
ISBN: 9783642337116
ISSN: 0302-9743
1611-3349
Conference Name: European Conference on Computer Vision (12th : 2012 : Florence, Italy)
Statement of
Responsibility: 
Rui Yao, Qinfeng Shi, Chunhua Shen, Yanning Zhang and Anton van den Hengel
Abstract: Robust visual tracking requires constant update of the target appearance model, but without losing track of previous appearance information. One of the difficulties with the online learning approach to this problem has been a lack of flexibility in the modelling of the inevitable variations in target and scene appearance over time. The traditional online learning approach to the problem treats each example equally, which leads to previous appearances being forgotten too quickly and a lack of emphasis on the most current observations. Through analysis of the visual tracking problem, we develop instead a novel weighted form of online risk which allows more subtlety in its representation. However, the traditional online learning framework does not accommodate this weighted form. We thus also propose a principled approach to weighted online learning using weighted reservoir sampling and provide a weighted regret bound as a theoretical guarantee of performance. The proposed novel online learning framework can handle examples with different importance weights for binary, multiclass, and even structured output labels in both linear and non-linear kernels. Applying the method to tracking results in an algorithm which is both efficient and accurate even in the presence of severe appearance changes. Experimental results show that the proposed tracker outperforms the current state-of-the-art.
Keywords: Computer imaging; image processing and computer vision; pattern recognition; biometrics; computer graphics; algorithm analysis and problem complexity
Rights: © Springer-Verlag Berlin Heidelberg 2012
RMID: 0020122956
DOI: 10.1007/978-3-642-33712-3_12
Grant ID: http://purl.org/au-research/grants/arc/DP1094764
http://purl.org/au-research/grants/arc/LE100100235
http://purl.org/au-research/grants/arc/DE120101161
http://purl.org/au-research/grants/arc/DP110103521
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


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