Anthropocentric Video Segmentation for Lecture Webcasts. (24th December 2007)

• Record Type: Journal Article
• Authors: Friedland, Gerald; Rojas, Raul
• Other Names: Pitas Ioannis Academic Editor.
• Is Part Of: EURASIP journal on image and video processing. Volume 2008(2008)
• Publication Date: 2007-12-24
• Subjects: Image processing -- Digital techniques -- Periodicals; Digital video -- Periodicals; Traitement d'images; Vidéo numérique; Digital video; Image processing -- Digital techniques; Periodicals; Electronic journal; Electronic journals; 621.367
• DOI: 10.1155/2008/195743
• Languages: English
• ISSNs: 1687-5176

Abstract

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.