Presentation 2005-03-25
Efficient and Effective Lifle-Log Video Summarization Based on Sampling of Sensor Data
Shinya KAWASAKI, Takayuki ISHIKAWA, Toshihiko YAMASAKI, Kiyoharu AIZAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Life log data are huge and redundant. Therefore, efficient summarization is needed. However, summarization using context data are seldom discussed. In this paper, we evaluate efficiency of summarization experimentally. We focus on spatio sampling and temporal sampling as summarization method. In our experiment, we defined two parameters to evaluate the summarized data : the rate of unique frame and the rate of event matching. As a result, we have obtained optimum conditions of sampling.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) life-log / spatio-temporal sampling / video summarization / context
Paper # MVE2004-80
Date of Issue

Conference Information
Committee MVE
Conference Date 2005/3/18(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 Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Efficient and Effective Lifle-Log Video Summarization Based on Sampling of Sensor Data
Sub Title (in English)
Keyword(1) life-log
Keyword(2) spatio-temporal sampling
Keyword(3) video summarization
Keyword(4) context
1st Author's Name Shinya KAWASAKI
1st Author's Affiliation Graduate School of Engineering, The Univ. of Tokyo()
2nd Author's Name Takayuki ISHIKAWA
2nd Author's Affiliation Graduate School of Frontier Sciences, The Univ. of Tokyo
3rd Author's Name Toshihiko YAMASAKI
3rd Author's Affiliation Graduate School of Frontier Sciences, The Univ. of Tokyo
4th Author's Name Kiyoharu AIZAWA
4th Author's Affiliation Graduate School of Engineering, The Univ. of Tokyo:Graduate School of Frontier Sciences, The Univ. of Tokyo
Date 2005-03-25
Paper # MVE2004-80
Volume (vol) vol.104
Number (no) 749
Page pp.pp.-
#Pages 6
Date of Issue