The automatic observation of team-sport games such as soccer is a valuable application domain for computer vision research. A practically applicable system in this domain has to reliably solve problems such as initialization and tracking of camera models, real-time object recognition and multiple object tracking through occlusions. ASpoGAMo stands for Automa-tic Sports Games Analysis Modell and consits of two subsystems. Firstly, a vision based sys-tem for extracting motion trajectories of all visible players from standard broadcast recordings of soccer games. This subsystem is also capable of infering the position of the ball. Secondly AspoGAMo provides a knowledge base containing also higher level abstractions of the posi-tion data and a query interface. http://www9.cs.tum.edu/projects/aspogamo/
© Copyright 2008 All rights reserved.