Presentation	2009-10-15 Video Retrieval using SIFT on Space-Time Images Representing Motions Kyota AOKI,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	There are many videos about sports. In sports videos, the motions carry much information about shots. This paper proposes the video retrieval system based on the motions. We have many criteria about sameness. The method retrieves videos based on the similarity of the all motions described in frames. The method gets the motions using the reliable motion estimation method, and makes the 1-dimensional projections from the X motion, Y motion and the reliabilities. Resulting image has the 1-dimensional space axis and the 1-dimensional time axis. On the images, using SIFT, the method retrieves shots as fast as the image retrievals do. This paper proposed the video retrieval method using SIFT and shows the experiments about baseball games.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	video retrieval / motion estimation / 1-dimensional projection / SIFT
Paper #	SIP2009-65,IE2009-90
Date of Issue

Conference Information
Committee	IE
Conference Date	2009/10/8(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	Image Engineering (IE)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Video Retrieval using SIFT on Space-Time Images Representing Motions
Sub Title (in English)
Keyword(1)	video retrieval
Keyword(2)	motion estimation
Keyword(3)	1-dimensional projection
Keyword(4)	SIFT
1st Author's Name	Kyota AOKI
1st Author's Affiliation	Graduate school of Engineering, Utsunomiya University()
Date	2009-10-15
Paper #	SIP2009-65,IE2009-90
Volume (vol)	vol.109
Number (no)	227
Page	pp.pp.-
#Pages	6
Date of Issue