The automated analysis of football games requires integrated computer and sensor systems that are capable of - acquiring motion data of the players and the ball, - interpreting these data in terms of intentional activities, such as dribblings and passes, and - assessing the game based on an abstract game model that is obtained through the interpretation of the data. The research project 'Sensor-based, Automatic Analysis of Football Games' is an ambitious, mid-term research project that studies the automation of these tasks. The main objectives of the project are (1) the investigation of novel computational mechanisms that enable computer systems to recognize intentional activities, (2) the development of an integrated software system to automate game interpretation and analysis, and (3) the demonstration of the impact of automated game analysis on application areas, such as sport science, football coaching, and sports entertainment. Basic and applied research in the project does not only cover the development of AI technologies, including probabilistic state estimation, recognition of intentional activities, machine learning and data mining, knowledge representation, and automated reasoning, but also their pragmatic integration with other technologies into a prototype system. We already test our system using videos from the games at the Football World Championship 2006 in Germany and other.
© Copyright 2008 Alle Rechte vorbehalten.