A Graph-based Feature Combination Approach to Object Tracking

View/ Open
Author(s)
Quang, Anh Nguyen
Robles-Kelly, Antonio
Zhou, Jun
Griffith University Author(s)
Year published
2010
Metadata
Show full item recordAbstract
In this paper, we present a feature combination approach to object tracking based upon graph embedding techniques. The method presented here abstracts the low complexity features used for purposes of tracking to a relational structure and employs graph-spectral methods to combine them. This gives rise to a feature combination scheme which minimises the mutual cross-correlation between features and is devoid of free parameters. It also allows an analytical solution making use of matrix factorisation techniques. The new target location is recovered making use of a weighted combination of target-centre shifts corresponding to ...
View more >In this paper, we present a feature combination approach to object tracking based upon graph embedding techniques. The method presented here abstracts the low complexity features used for purposes of tracking to a relational structure and employs graph-spectral methods to combine them. This gives rise to a feature combination scheme which minimises the mutual cross-correlation between features and is devoid of free parameters. It also allows an analytical solution making use of matrix factorisation techniques. The new target location is recovered making use of a weighted combination of target-centre shifts corresponding to each of the features under study, where the feature weights arise from a cost function governed by the embedding process. This treatment permits the update of the feature weights in an on-line fashion in a straightforward manner. We illustrate the performance of our method in real-world image sequences and compare our results to a number of alternatives.
View less >
View more >In this paper, we present a feature combination approach to object tracking based upon graph embedding techniques. The method presented here abstracts the low complexity features used for purposes of tracking to a relational structure and employs graph-spectral methods to combine them. This gives rise to a feature combination scheme which minimises the mutual cross-correlation between features and is devoid of free parameters. It also allows an analytical solution making use of matrix factorisation techniques. The new target location is recovered making use of a weighted combination of target-centre shifts corresponding to each of the features under study, where the feature weights arise from a cost function governed by the embedding process. This treatment permits the update of the feature weights in an on-line fashion in a straightforward manner. We illustrate the performance of our method in real-world image sequences and compare our results to a number of alternatives.
View less >
Conference Title
COMPUTER VISION - ACCV 2009, PT II
Volume
5995
Issue
PART 2
Copyright Statement
© 2009 Springer Berlin/Heidelberg. This is the author-manuscript version of this paper. Reproduced in accordance with the copyright policy of the publisher.The original publication is available at www.springerlink.com
Subject
Computer vision