Presentation 2005-03-17
Robust Background Subtraction by Bi-polar Radial Reach Correlation
Yutaka SATOH, Katsuhiko SAKAUE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The background subtraction algorithm is a frequently-used object segmentation technique because of its algorithmic simplicity. Especially, simple background subtraction has been used because of its low processing costs and ease of implementation. However, the method is susceptible to illumination change such as shadows, and when the brightness differences between objects and the background are small, it cannot detect the difference. In order to resolve these problems, we have proposed a novel algorithm for robust object detection and segmentation, which is based on a new robust dissimilarity measure called as Radial Reach Correlation(RRC). The RRC evaluates a local texture between a background image and a current scene to realize robust object detection under poor conditions. This time, we have improved the method to make it more reliable, especially when the image has a weak texture.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) background subtraction / segmentation / texture / robust statistics
Paper # TL2004-56,PRMU2004-224
Date of Issue

Conference Information
Committee TL
Conference Date 2005/3/10(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Thought and Language (TL)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Robust Background Subtraction by Bi-polar Radial Reach Correlation
Sub Title (in English)
Keyword(1) background subtraction
Keyword(2) segmentation
Keyword(3) texture
Keyword(4) robust statistics
1st Author's Name Yutaka SATOH
1st Author's Affiliation Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology(AIST)()
2nd Author's Name Katsuhiko SAKAUE
2nd Author's Affiliation Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology(AIST)
Date 2005-03-17
Paper # TL2004-56,PRMU2004-224
Volume (vol) vol.104
Number (no) 739
Page pp.pp.-
#Pages 6
Date of Issue