EURASIP Journal on Image and Video Processing
Volume 2008 (2008), Article ID 195743, 10 pages
doi:10.1155/2008/195743
Research Article

Anthropocentric Video Segmentation for Lecture Webcasts

Gerald Friedland1 and Raul Rojas2

1International Computer Science Institute, 1947 Center Street, Suite 600 Berkeley, CA 94704-1198, USA
2Institut für Informatik, Freie Universität Berlin, Takustrasse 9, Berlin 14195, Germany

Received 31 January 2007; Revised 16 July 2007; Accepted 12 December 2007

Academic Editor: Ioannis Pitas

Copyright © 2008 Gerald Friedland and Raul Rojas. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

Many lecture recording and presentation systems transmit slides or chalkboard content along with a small video of the instructor. As a result, two areas of the screen are competing for the viewer's attention, causing the widely known split-attention effect. Face and body gestures, such as pointing, do not appear in the context of the slides or the board. To eliminate this problem, this article proposes to extract the lecturer from the video stream and paste his or her image onto the board or slide image. As a result, the lecturer acting in front of the board or slides becomes the center of attention. The entire lecture presentation becomes more human-centered. This article presents both an analysis of the underlying psychological problems and an explanation of signal processing techniques that are applied in a concrete system. The presented algorithm is able to extract and overlay the lecturer online and in real time at full video resolution.