Time: 2:00pm Tuesday, 12th May.
Location: SIT 459
Speaker: Michael Horton, University of Sydney
Title: Automated Classification of Passing in Football
A knowledgeable observer of a game of football (soccer) can
make a subjective evaluation of the quality of passes made between play-
ers during the game. In this paper we consider the problem of producing
an automated system to make the same evaluation of passes.We present a
model that constructs numerical predictor variables from spatiotemporal
match data using feature functions based on methods from computa-
tional geometry, and then learns a classication function from labelled
examples of the predictor variables. In addition, we show that the pre-
dictor variables computed using methods from computational geometry
are among the most important to the learned classiers.