Presentation 2001/7/11
Scene Change Detection from Video Sequence Based on Discriminant Method
Ken-ichirou SUZUKI, Masaomi NAKAJIMA, Hitoshi SAKANO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose the movement direction histogram as new features for the scene change detection. Until now, it has been proposed that we solve the scene change detection as a dichotomy problem. However, we have the problem that the scene with the intense movement was mistaken for the scene change. Then, in this paper, we propose the movement direction histogram features(MDH) to solve thess problems. This makes the histogram of the direction on motion vector required between adjoining frames. The MDH feature decrease false detection of scene change that caused by intense movement. In the experiment, detection accuracy improved about 29% in comparison with the conventional method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Scene Change Detection / Video Indexing / Motion Vector / Discriminant Analysis
Paper # IE2001-27,PRMU2001-47,MVE2001-26
Date of Issue

Conference Information
Committee MVE
Conference Date 2001/7/11(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) Scene Change Detection from Video Sequence Based on Discriminant Method
Sub Title (in English)
Keyword(1) Scene Change Detection
Keyword(2) Video Indexing
Keyword(3) Motion Vector
Keyword(4) Discriminant Analysis
1st Author's Name Ken-ichirou SUZUKI
1st Author's Affiliation NTT DATA CORPORATION()
2nd Author's Name Masaomi NAKAJIMA
2nd Author's Affiliation NTT DATA CORPORATION
3rd Author's Name Hitoshi SAKANO
3rd Author's Affiliation NTT DATA CORPORATION
Date 2001/7/11
Paper # IE2001-27,PRMU2001-47,MVE2001-26
Volume (vol) vol.101
Number (no) 204
Page pp.pp.-
#Pages 8
Date of Issue