Presentation 2009-03-14
Object Segmentation Based on Adaptive Background Model Considering Spatio-temporal Features
Tatsuya Tanaka, Atsushi Shimada, Daisaku Arita, Rin-ichiro Taniguchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a new method for background modeling considering spatio-temporal features. Our method consists of three complementary approaches. The pixel-level background model uses the probability density function to approximate background model. The PDF is estimated non-parametrically by using Parzen density estimation. The region-level background model is based on the evaluation of the local texture at pixel-level resolution while reducing the effects of variations in lighting. And the frame-level background model detects sudden, global changes in the image and estimates a present background image from input image and original background image. Then, the moving object is extracted by background subtraction. Fusing their approaches realizes robust object detection under varying illumination. Several experiments show the effectiveness of our approach.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Adaptive background model / Illumination change / Parzen density estimation / Radial Reach Correlation
Paper # PRMU2008-282
Date of Issue

Conference Information
Committee PRMU
Conference Date 2009/3/6(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Object Segmentation Based on Adaptive Background Model Considering Spatio-temporal Features
Sub Title (in English)
Keyword(1) Adaptive background model
Keyword(2) Illumination change
Keyword(3) Parzen density estimation
Keyword(4) Radial Reach Correlation
1st Author's Name Tatsuya Tanaka
1st Author's Affiliation Department of Intelligent Systems, Kyushu University()
2nd Author's Name Atsushi Shimada
2nd Author's Affiliation Department of Intelligent Systems, Kyushu University
3rd Author's Name Daisaku Arita
3rd Author's Affiliation Institute of Systems, Information Technologies and Nanotechnologies
4th Author's Name Rin-ichiro Taniguchi
4th Author's Affiliation Department of Intelligent Systems, Kyushu University
Date 2009-03-14
Paper # PRMU2008-282
Volume (vol) vol.108
Number (no) 484
Page pp.pp.-
#Pages 6
Date of Issue