Presentation 2001/1/12
Video Stream Selection for Remote Lecture Based on Degree of Students' Attention
Takuro SAKIYAMA, MUKUNOKI Masayuki /, Michihiko MINOH, Katsuo IKEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a method of video stream selection for remote lectures based on degree of students' attention. First, we detect students' face areas in video streams of lecture room with normalized correlation operation, and judge a direction of each student's face by the distribution of skin area. Next, we calculate the degree of students' attention to each target from a combination of the direction of students' face and the layout of the room, and then we select a video stream transmitted to remote lecture rooms according to the degree of attention. We apply our method to simulated lectures and evaluate its performance.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) remote lecture / video stream selection / face direction detection
Paper # PRMU2000-182
Date of Issue

Conference Information
Committee PRMU
Conference Date 2001/1/12(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Video Stream Selection for Remote Lecture Based on Degree of Students' Attention
Sub Title (in English)
Keyword(1) remote lecture
Keyword(2) video stream selection
Keyword(3) face direction detection
1st Author's Name Takuro SAKIYAMA
1st Author's Affiliation Graduate School of Informatics, Kyoto University()
2nd Author's Name MUKUNOKI Masayuki /
2nd Author's Affiliation Graduate School of Informatics, Kyoto University
3rd Author's Name Michihiko MINOH
3rd Author's Affiliation Graduate School of Informatics, Kyoto University
4th Author's Name Katsuo IKEDA
4th Author's Affiliation Graduate School of Informatics, Kyoto University
Date 2001/1/12
Paper # PRMU2000-182
Volume (vol) vol.100
Number (no) 566
Page pp.pp.-
#Pages 8
Date of Issue