Presentation 2011-02-18
Partial Matching Method using Spatio-temporal Regularized Canonical Correlation Analysis
Yoshiaki KODAMA, Takumi KOBAYASHI, Nobuyuki OTSU, Kazuhiro FUKUI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is a fundamental and important procedure to detect similar regions from some images or videos. We propose a novel method for partial matching in the framework of canonical correlation analysis (CCA) incorporating the regularization based on spatio-temporal continuity. The proposed method can detect matched spatio-temporal regions without explicitly segmenting those. In experiments, we applied the method to motion detection and object detection and confirmed the effectiveness.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Partial Matching / Canonical Correlation Analysis / Spatio-temporal Regularization / Object Detection / Motion Detection
Paper # PRMU2010-223
Date of Issue

Conference Information
Committee PRMU
Conference Date 2011/2/10(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) Partial Matching Method using Spatio-temporal Regularized Canonical Correlation Analysis
Sub Title (in English)
Keyword(1) Partial Matching
Keyword(2) Canonical Correlation Analysis
Keyword(3) Spatio-temporal Regularization
Keyword(4) Object Detection
Keyword(5) Motion Detection
1st Author's Name Yoshiaki KODAMA
1st Author's Affiliation University of Tsukuba, Graduate School of Systems and Information Engineering()
2nd Author's Name Takumi KOBAYASHI
2nd Author's Affiliation National Institute of Advanced Industrial Science and Technology
3rd Author's Name Nobuyuki OTSU
3rd Author's Affiliation National Institute of Advanced Industrial Science and Technology
4th Author's Name Kazuhiro FUKUI
4th Author's Affiliation University of Tsukuba, Graduate School of Systems and Information Engineering
Date 2011-02-18
Paper # PRMU2010-223
Volume (vol) vol.110
Number (no) 414
Page pp.pp.-
#Pages 6
Date of Issue