Comparison of Background Subtraction Methods for a Multimedia Learning Space

Fida El Baf, Thierry Bouwmans, Bertrand Vachon. Comparison of Background Subtraction Methods for a Multimedia Learning Space. In Sérgio M. M. de Faria, Pedro A. Amado Assunção, editors, SIGMAP 2007 - Proceedings of the Second International Conference on Signal Processing and Multimedia Applications, Barcelona, Spain, July 28-31, 2007, SIGMAP is part of ICETE - The International Joint Conference on e-Business and Telecommunications. pages 153-158, INSTICC Press, 2007.


This article presents, at a first time, a multimedia application called Aqu@theque. This project consists in elaborating a multimedia system dedicated to aquariums which gives ludo-pedagogical information in an interactive learning area. The reliability of this application depends of the segmentation and recognition steps. Then, we focus on the segmentation step using the background subtraction principle. Our motivation is to compare different background subtraction methods used to detect fishes in video sequences and to improve the performance of this application. In this context, we present a new classification of the critical situations which occurred in videos and disturbed the assumptions made in background subtraction methods. This classification can be used in any application using background subtraction like video surveillance, motion capture or video games.