University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Robust visual tracking using structural region hierarchy and graph matching

Song, Yi-Zhe, Li, C., Wang, L., Hall, P. and Shen, P. (2012) Robust visual tracking using structural region hierarchy and graph matching Neurocomputing, 89. pp. 12-20.

Full text not available from this repository.


Visual tracking aims to match objects of interest in consecutive video frames. This paper proposes a novel and robust algorithm to address the problem of object tracking. To this end, we investigate the fusion of state-of-the-art image segmentation hierarchies and graph matching. More specifically, (i) we represent the object to be tracked using a hierarchy of regions, each of which is described with a combined feature set of SIFT descriptors and color histograms; (ii) we formulate the tracking process as a graph matching problem, which is solved by minimizing an energy function incorporating appearance and geometry contexts; and (iii) more importantly, an effective graph updating mechanism is proposed to adapt to the object changes over time for ensuring the tracking robustness. Experiments are carried out on several challenging sequences and results show that our method performs well in terms of object tracking, even in the presence of variations of scale and illumination, moving camera, occlusion, and background clutter.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Li, C.
Wang, L.
Hall, P.
Shen, P.
Date : 15 July 2012
DOI : 10.1016/j.neucom.2011.11.030
Uncontrolled Keywords : Graph matching; Image hierarchy; Tracking
Depositing User : Clive Harris
Date Deposited : 30 Jul 2019 08:58
Last Modified : 30 Jul 2019 08:58

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800