Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/56414
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Effective Appearance Model and Similarity Measure for Particle Filtering and Visual Tracking |
Author: | Wang, H. Suter, D. Schindler, K. |
Citation: | Proceedings of the 9th European Conference on Computer Vision, Graz, Austria,7-13 May, 2006., pp.606-618 |
Publisher: | Springer |
Publisher Place: | Berlin |
Issue Date: | 2006 |
Series/Report no.: | Lecture Notes in Computer Science, Computer Vision – ECCV 2006 ; v. 3953 |
ISBN: | 3540338322 9783540338369 |
ISSN: | 0302-9743 1611-3349 |
Conference Name: | European Conference on Computer Vision (9th : 2006 : Graz, Austria) |
Editor: | Leonardis, A. Pinz, A. |
Statement of Responsibility: | Hanzi Wang, David Suter and Konrad Schindler |
Abstract: | In this paper, we adaptively model the appearance of objects based on Mixture of Gaussians in a joint spatial-color space (the approach is called SMOG). We propose a new SMOG-based similarity measure. SMOG captures richer information than the general color histogram because it incorporates spatial layout in addition to color. This appearance model and the similarity measure are used in a framework of Bayesian probability for tracking natural objects. In the second part of the paper, we propose an Integral Gaussian Mixture (IGM) technique, as a fast way to extract the parameters of SMOG for target candidate. With IGM, the parameters of SMOG can be computed efficiently by using only simple arithmetic operations (addition, subtraction, division) and thus the computation is reduced to linear complexity. Experiments show that our method can successfully track objects despite changes in foreground appearance, clutter, occlusion, etc.; and that it outperforms several color-histogram based methods. |
DOI: | 10.1007/11744078_47 |
Published version: | http://dx.doi.org/10.1007/11744078_47 |
Appears in Collections: | Aurora harvest 5 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.