An efficient real-time system for active video conferencing

DOI

10.2991/jcis.2006.71How to use a DOI?

Keywords

Head tracking, Kalman filtering, video conferencing

Abstract

This paper describes a new approach for implementation of an efficient real-time system proper for using in active video conferencing sessions. A camera tracks presenter’s head and its movements and orientations in an unconstrained environment automatically by its pan and tilt actions. Head or face is modeled by an ellipse using least square ellipse fitting algorithm. Linear Kalman filter is employed effectively, in addition to a measurement model based on bimodal color information. Experimental results demonstrate the effectiveness of the proposed system in overcoming challenges that trackers are facing in real world environments.

Copyright

© 2006, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Leila Sabeti
AU  - Q. M. Jonathan Wu
AU  - Jason Z. Zhang
PY  - 2006/10
DA  - 2006/10
TI  - An efficient real-time system for active video conferencing
BT  - Proceedings of the 9th Joint International Conference on Information Sciences (JCIS-06)
PB  - Atlantis Press
SN  - 1951-6851
UR  - https://doi.org/10.2991/jcis.2006.71
DO  - 10.2991/jcis.2006.71
ID  - Sabeti2006/10
ER  -