Presentation 2012-07-19
Similar Video Retrieval Method based on the Coarsened SURF
Noboru MURABAYASHI, Kenichi YOSHIDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Supposing video frame size is 720 × 480 and video retrieval are conducted using local features, there are thousands of key points within a frame image. Therefore a large amount of memory capacity required. To cope with this problem we propose similar video retrieval method based on the coarsened SURF. SURF processing are conducted in a size of 90 × 60 thumbnail frame image. After this processing, coarsened SURF data are created based on the binary processing. Experiment result shows average detection accuracy is 90%.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) SURF / coarsen / direct-mapped cache / hash / keypoint
Paper # MoMuC2012-14,IE2012-39
Date of Issue

Conference Information
Committee MoMuC
Conference Date 2012/7/12(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 Mobile Multimedia Communications(MoMuC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Similar Video Retrieval Method based on the Coarsened SURF
Sub Title (in English)
Keyword(1) SURF
Keyword(2) coarsen
Keyword(3) direct-mapped cache
Keyword(4) hash
Keyword(5) keypoint
1st Author's Name Noboru MURABAYASHI
1st Author's Affiliation Information and Scocial Science Research Group, Graduate School of Business Sciences, University of Tsukuba()
2nd Author's Name Kenichi YOSHIDA
2nd Author's Affiliation Information and Scocial Science Research Group, Graduate School of Business Sciences, University of Tsukuba
Date 2012-07-19
Paper # MoMuC2012-14,IE2012-39
Volume (vol) vol.112
Number (no) 135
Page pp.pp.-
#Pages 6
Date of Issue