Issue No. 03 - July-September (2005 vol. 4)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MPRV.2005.53
Michael Beetz , Technische Universit?t M?nchen
Bernhard Kirchlechner , Technische Universit?t M?nchen
Martin Lames , Universit?t Augsburg
Real-time game analysis systems must be able to automatically recognize intentional activities in a multiagent system with continually acting agents. To meet these demands, the authors developed the Football Interaction and Process Model and a software system that can acquire, interpret, and analyze this model. The system can acquire models of player skills, infer action-selection criteria, and determine player and team strengths and weaknesses. They tested it on the RoboCup simulation league and received promising results.<p>This article is part of a special issue on pervasive computing in sports. </p>
real-time positioning system, learning action models, interpretation of intentional activity
M. Beetz, M. Lames and B. Kirchlechner, "Computerized Real-Time Analysis of Football Games," in IEEE Pervasive Computing, vol. 4, no. , pp. 33-39, 2005.