Presentation 2006-07-13
Invasion Detection based on High Reliable Motion Estimation and Background Subtraction
Yuji INO, Masashi NOBE, Kyota AOKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes an intrusion detection method using reliable motion estimations. The reliable motion estimation method uses block-matching, improved luminance projection method, and etc. A motion estimating result is a collection of triples of reliable ratio, place and motion. Using the method, we have blocks that have no motion. Between corresponding no motion blocks, the difference of average intensities represent the difference of average illuminations. The proposed intrusion detection method compensates the difference of illuminations. Then, classical image differencing method decides the intrusions. We implement the proposed method and show the experimental results. The experimental results show that the proposed method can compensate illumination differences. Our implementation is fast enough for real usages.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) motion estimation / block matching / invasion detection / illumination compensation
Paper # IE2006-21,MVE2006-27
Date of Issue

Conference Information
Committee MVE
Conference Date 2006/7/6(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 Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Invasion Detection based on High Reliable Motion Estimation and Background Subtraction
Sub Title (in English)
Keyword(1) motion estimation
Keyword(2) block matching
Keyword(3) invasion detection
Keyword(4) illumination compensation
1st Author's Name Yuji INO
1st Author's Affiliation Faculty of Engineering, Utsunomiya University()
2nd Author's Name Masashi NOBE
2nd Author's Affiliation Faculty of Engineering, Utsunomiya University
3rd Author's Name Kyota AOKI
3rd Author's Affiliation Faculty of Engineering, Utsunomiya University
Date 2006-07-13
Paper # IE2006-21,MVE2006-27
Volume (vol) vol.106
Number (no) 157
Page pp.pp.-
#Pages 6
Date of Issue