Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/67306
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Robust Foreground Segmentation Based on Two Effective Background Models |
Author: | Li, X. Hu, W. Zhang, Z. Zhang, X. |
Citation: | MM’08 : Proceedings of the 2008 ACM International Conference on Multimedia, with co-located Symposium & Workshops Vancouver, BC, Canada, October 27–31, 2008 / pp.223-228 |
Publisher: | ACM Press |
Publisher Place: | New York |
Issue Date: | 2008 |
ISBN: | 9781605583129 |
Conference Name: | ACM International Conference on Multimedia Information Retrieval (1st : 2008 : Vancouver, Canada) |
Statement of Responsibility: | Xi Li, Weiming Hu, Zhongfei Zhang, Xiaoqin Zhang |
Abstract: | Foreground segmentation is a common foundation for many computer vision applications such as tracking and behavior analysis. Most existing algorithms for foreground segmentation learn pixel-based statistical models, which are sensitive to dynamic scenes such as illumination change, shadow movement, and swaying trees. In order to address this problem, we propose two block-based background models using the recently developed incremental rank-(R1, R2, R3) tensor-based subspace learning algorithm (referred to as IRTSA [1]). These two IRTSA-based background models (i.e., IRTSAGBM and IRTSA-CBM respectively for grayscale and color images) incrementally learn low-order tensor-based eigenspace representations to fully capture the intrinsic spatio-temporal characteristics of a scene, leading to robust foreground segmentation results. Theoretic analysis and experimental evaluations demonstrate the promise and effectiveness of the proposed background models. |
Keywords: | Video surveillance object detection |
Rights: | Copyright 2008 ACM |
DOI: | 10.1145/1460096.1460133 |
Description (link): | http://press.liacs.nl/mir2008/index.html |
Published version: | http://dx.doi.org/10.1145/1460096.1460133 |
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.