Automatic multi-modal meeting camera selection for video-conferences and meeting browsers

Marc Al-Hames; Benedikt Hörnler; Ronald Müller; Joachim Schenk; Gerhard Rigoll

doi:10.1109/icme.2007.4285090

Automatic multi-modal meeting camera selection for video-conferences and meeting browsers

Marc Al-Hames, Benedikt Hörnler, Ronald Müller, Joachim Schenk, Gerhard Rigoll

Chair of Human-Machine Communication

Technical University of Munich

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Scopus citations

Abstract

In a video-conference the participants usually see the video of the speaker. However if somebody reacts (e. g. nodding) the system should switch to his video. Current systems do not support this. We formulate this camera selection as a pattern recognition problem. Then we apply HMMs to learn this behaviour. Thus our system can easily be adapted to different meeting scenarios. Furthermore, while current systems stay on the speaker, our system will switch if somebody reacts. In an experimental section we show that - compared to a desired output - a current system shows the wrong camera more than half of the time (frame error rate 53%), where our system selects the wrong camera in only a quarter of the time (FER 27%).

Original language	English
Title of host publication	Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007
Publisher	IEEE Computer Society
Pages	2074-2077
Number of pages	4
ISBN (Print)	1424410177, 9781424410170
DOIs	https://doi.org/10.1109/icme.2007.4285090
State	Published - 2007
Event	IEEE International Conference onMultimedia and Expo, ICME 2007 - Beijing, China Duration: 2 Jul 2007 → 5 Jul 2007

Publication series

Name	Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007

Conference

Conference	IEEE International Conference onMultimedia and Expo, ICME 2007
Country/Territory	China
City	Beijing
Period	2/07/07 → 5/07/07

Access to Document

10.1109/icme.2007.4285090

Cite this

Al-Hames, M., Hörnler, B., Müller, R., Schenk, J., & Rigoll, G. (2007). Automatic multi-modal meeting camera selection for video-conferences and meeting browsers. In Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007 (pp. 2074-2077). Article 4285090 (Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007). IEEE Computer Society. https://doi.org/10.1109/icme.2007.4285090

Al-Hames, Marc ; Hörnler, Benedikt ; Müller, Ronald et al. / Automatic multi-modal meeting camera selection for video-conferences and meeting browsers. Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007. IEEE Computer Society, 2007. pp. 2074-2077 (Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007).

@inproceedings{bf9aab3f6176478a83cf54294d276895,

title = "Automatic multi-modal meeting camera selection for video-conferences and meeting browsers",

abstract = "In a video-conference the participants usually see the video of the speaker. However if somebody reacts (e. g. nodding) the system should switch to his video. Current systems do not support this. We formulate this camera selection as a pattern recognition problem. Then we apply HMMs to learn this behaviour. Thus our system can easily be adapted to different meeting scenarios. Furthermore, while current systems stay on the speaker, our system will switch if somebody reacts. In an experimental section we show that - compared to a desired output - a current system shows the wrong camera more than half of the time (frame error rate 53%), where our system selects the wrong camera in only a quarter of the time (FER 27%).",

author = "Marc Al-Hames and Benedikt H{\"o}rnler and Ronald M{\"u}ller and Joachim Schenk and Gerhard Rigoll",

year = "2007",

doi = "10.1109/icme.2007.4285090",

language = "English",

isbn = "1424410177",

series = "Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007",

publisher = "IEEE Computer Society",

pages = "2074--2077",

booktitle = "Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007",

note = "IEEE International Conference onMultimedia and Expo, ICME 2007 ; Conference date: 02-07-2007 Through 05-07-2007",

}

Al-Hames, M, Hörnler, B, Müller, R, Schenk, J & Rigoll, G 2007, Automatic multi-modal meeting camera selection for video-conferences and meeting browsers. in Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007., 4285090, Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007, IEEE Computer Society, pp. 2074-2077, IEEE International Conference onMultimedia and Expo, ICME 2007, Beijing, China, 2/07/07. https://doi.org/10.1109/icme.2007.4285090

Automatic multi-modal meeting camera selection for video-conferences and meeting browsers. / Al-Hames, Marc; Hörnler, Benedikt; Müller, Ronald et al.
Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007. IEEE Computer Society, 2007. p. 2074-2077 4285090 (Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automatic multi-modal meeting camera selection for video-conferences and meeting browsers

AU - Al-Hames, Marc

AU - Hörnler, Benedikt

AU - Müller, Ronald

AU - Schenk, Joachim

AU - Rigoll, Gerhard

PY - 2007

Y1 - 2007

N2 - In a video-conference the participants usually see the video of the speaker. However if somebody reacts (e. g. nodding) the system should switch to his video. Current systems do not support this. We formulate this camera selection as a pattern recognition problem. Then we apply HMMs to learn this behaviour. Thus our system can easily be adapted to different meeting scenarios. Furthermore, while current systems stay on the speaker, our system will switch if somebody reacts. In an experimental section we show that - compared to a desired output - a current system shows the wrong camera more than half of the time (frame error rate 53%), where our system selects the wrong camera in only a quarter of the time (FER 27%).

AB - In a video-conference the participants usually see the video of the speaker. However if somebody reacts (e. g. nodding) the system should switch to his video. Current systems do not support this. We formulate this camera selection as a pattern recognition problem. Then we apply HMMs to learn this behaviour. Thus our system can easily be adapted to different meeting scenarios. Furthermore, while current systems stay on the speaker, our system will switch if somebody reacts. In an experimental section we show that - compared to a desired output - a current system shows the wrong camera more than half of the time (frame error rate 53%), where our system selects the wrong camera in only a quarter of the time (FER 27%).

UR - http://www.scopus.com/inward/record.url?scp=46449138729&partnerID=8YFLogxK

U2 - 10.1109/icme.2007.4285090

DO - 10.1109/icme.2007.4285090

M3 - Conference contribution

AN - SCOPUS:46449138729

SN - 1424410177

SN - 9781424410170

T3 - Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007

SP - 2074

EP - 2077

BT - Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007

PB - IEEE Computer Society

T2 - IEEE International Conference onMultimedia and Expo, ICME 2007

Y2 - 2 July 2007 through 5 July 2007

ER -

Al-Hames M, Hörnler B, Müller R, Schenk J, Rigoll G. Automatic multi-modal meeting camera selection for video-conferences and meeting browsers. In Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007. IEEE Computer Society. 2007. p. 2074-2077. 4285090. (Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007). doi: 10.1109/icme.2007.4285090

Automatic multi-modal meeting camera selection for video-conferences and meeting browsers

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this