Presentation 2007-09-03
An Improved Method for Background Subtraction and Its Application to Tracking of Moving Objects
Noriyuki Kawashima, Nozomu Nakamura, Rika Hagiwara, Hiroshi Hanaizumi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a new method for the background subtraction with statistical test for detecting moving objects. There are two methods; optical flow and background subtraction, to detect moving objects. The former has high performance to detect in movement, but gives us blurred edges. In the point of view of accurate edge detection, the latter has better performance than the former does. The background subtraction method, however, gives us noises by the swing of a camera in actual shooting environment. The proposed method introduces the mahalanobis distance for suppressing scene fluctuation effects and density normalization for avoiding the shadow effects. Furthermore we propose two systems application of detection of moving objects; a system for emergent detecting objects and a system for tracing moving objects using plural cameras.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # PRMU2007-50,HIP2007-59
Date of Issue

Conference Information
Committee HIP
Conference Date 2007/8/27(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 Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Improved Method for Background Subtraction and Its Application to Tracking of Moving Objects
Sub Title (in English)
Keyword(1)
1st Author's Name Noriyuki Kawashima
1st Author's Affiliation Graduate School of Computer and Information Sciences, Hosei University()
2nd Author's Name Nozomu Nakamura
2nd Author's Affiliation Graduate School of Computer and Information Sciences, Hosei University
3rd Author's Name Rika Hagiwara
3rd Author's Affiliation Graduate School of Computer and Information Sciences, Hosei University
4th Author's Name Hiroshi Hanaizumi
4th Author's Affiliation Graduate School of Computer and Information Sciences, Hosei University
Date 2007-09-03
Paper # PRMU2007-50,HIP2007-59
Volume (vol) vol.107
Number (no) 207
Page pp.pp.-
#Pages 6
Date of Issue