Presentation 2007/6/7
Moving Object Detection by Adaptive Background Subtraction including Nonlinear Processing
Kenichi YASUI, Megumi TAKEZAWA, Hirofumi SANADA, Kazuhisa WATANABE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Moving object detection from a video sequence is an important task in video analysis for such purposes as traffic monitoring and video surveillance. One of the frequently used techniques for the detection is background subtraction. The background image is maintained by background subtraction, and background subtraction enables detection of moving objects by thresholding the difference between a current frame image and the background image. This technique is simple and has good performance if the background image and the threshold are correct. However, it is difficult to maintain the correct background image and the threshold when the background is changed by illumination conditions. In this paper, an effective background subtraction technique that solves this problem is proposed. The proposed method enables maintenance of an appropriate background image and threshold and enables accurate detection of moving objects under the condition of changing illumination.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) background subtraction method / varying illumination / moving object detection / nonlinear processing
Paper # SIS2007-5
Date of Issue

Conference Information
Committee SIS
Conference Date 2007/6/7(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 Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Moving Object Detection by Adaptive Background Subtraction including Nonlinear Processing
Sub Title (in English)
Keyword(1) background subtraction method
Keyword(2) varying illumination
Keyword(3) moving object detection
Keyword(4) nonlinear processing
1st Author's Name Kenichi YASUI
1st Author's Affiliation Graduate School of Electrical Engineering, Hokkaido Institute of Technology()
2nd Author's Name Megumi TAKEZAWA
2nd Author's Affiliation Department of Information network Engineering, Hokkaido Institute of Technology
3rd Author's Name Hirofumi SANADA
3rd Author's Affiliation Department of Information network Engineering, Hokkaido Institute of Technology
4th Author's Name Kazuhisa WATANABE
4th Author's Affiliation Department of Information network Engineering, Hokkaido Institute of Technology
Date 2007/6/7
Paper # SIS2007-5
Volume (vol) vol.107
Number (no) 93
Page pp.pp.-
#Pages 4
Date of Issue