Presentation 2007-10-25
Image Registration Method of Multiple Motion-Regions and Its Applications(Internationa Session 2)
SoonKeun CHANG, Masao SHIMIZU, Masatoshi OKUTOMI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we propose an accurate method of registering an input image to a reference image with detecting automatically the multiple motion-regions from an image sequence taken with a hand-held camera. In the first step of the proposed method, detecting the most dominant motion-region from the reference image is performed by setting the whole image as ROI (region of interest). Subsequently, the second dominant motion-region is detected from the remaining region ; the multiple motion-regions are extracted automatically by repeating this process. The proposed method can accurately estimate motion parameters associated with the motion-regions to align the input image to the reference image. Additionally, we present applications of the proposed method. The validity of the proposed method is confirmed by performing experiments on real images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) image sequence / multiple motion-regions / registration / mask / super-resolution / object elimination
Paper # PRMU2007-102
Date of Issue

Conference Information
Committee PRMU
Conference Date 2007/10/18(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image Registration Method of Multiple Motion-Regions and Its Applications(Internationa Session 2)
Sub Title (in English)
Keyword(1) image sequence
Keyword(2) multiple motion-regions
Keyword(3) registration
Keyword(4) mask
Keyword(5) super-resolution
Keyword(6) object elimination
1st Author's Name SoonKeun CHANG
1st Author's Affiliation Graduate School of Science and Engineering, Tokyo Institute of Technology()
2nd Author's Name Masao SHIMIZU
2nd Author's Affiliation Graduate School of Science and Engineering, Tokyo Institute of Technology
3rd Author's Name Masatoshi OKUTOMI
3rd Author's Affiliation Graduate School of Science and Engineering, Tokyo Institute of Technology
Date 2007-10-25
Paper # PRMU2007-102
Volume (vol) vol.107
Number (no) 281
Page pp.pp.-
#Pages 6
Date of Issue