Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/67332
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Graph Based Discriminative Learning for Robust and Efficient Object Tracking
Author: Zhang, X.
Hu, W.
Maybank, S.
Li, X.
Citation: IEEE 12th International Conference on Computer Vision 2007: pp.1-8
Publisher: IEEE
Publisher Place: Online
Issue Date: 2007
ISBN: 9781424416318
Conference Name: IEEE International Conference on Computer Vision (11th : 2007 : Rio de Janeiro, Brazil)
Statement of
Responsibility: 
Xiaoqin Zhang, Weiming Hu, Steve Maybank, Xi Li
Abstract: Object tracking is viewed as a two-class 'one-versus-rest' classification problem, in which the sample distribution of the target is approximately Gaussian while the background samples are often multimodal. Based on these special properties, we propose a graph embedding based discriminative learning method, in which the topology structures of graphs are carefully designed to reflect the properties of the sample distributions. This method can simultaneously learn the subspace of the target and its local discriminative structure against the background. Moreover, a heuristic negative sample selection scheme is adopted to make the classification more effective. In tracking procedure, the graph based learning is embedded into a Bayesian inference framework cascaded with hierarchical motion estimation, which significantly improves the accuracy and efficiency of the localization. Furthermore, an incremental updating technique for the graphs is developed to capture the changes in both appearance and illumination. Experimental results demonstrate that, compared with two state-of-the-art methods, the proposed tracking algorithm is more efficient and effective, especially in dynamically changing and clutter scenes.
Rights: ©2007 IEEE
RMID: 0020112707
DOI: 10.1109/ICCV.2007.4409034
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.