ASpoGAMo: Automated Sports Game Analysis Models
Michael Beetz, Nicolai v. Hoyningen-Huene, Bernhard Kirchlechner, Suat Gedikli, Francisco Siles-Canales, Murat Duruş, Martin Lames · 2009
Abstract. We propose automated sport game models as a novel technical means for the analysis of team sport games. The basic idea is that automated sport game models are based on a conceptualization of key notions in such games and probabilistically derived from a set of previous games. In contrast to existing approaches, automated sport game models provide an analysis that is sensitive to their context and go beyond simple statistical aggregations allowing objective, transparent and meaningful concept definitions. Based on automatically gathered spatio-temporal data by a computer vision system, a model hierarchy is built bottom up, where context-sensitive concepts are instantiated by the application of machine learning techniques. We describe the current state of implementation of the ASPOGAMO system including its computer vision subsystem that realizes the idea of automated sport game models. Their usage is exemplified with an analysis of the final of the soccer World Cup 2006.