Research Project: Detecting Violations in Table Soccer Games Using Naive Bayes Classifiers
Abstract
In table soccer, humans can not always accurately observe fast actions like rod spins and kicks. However, this is necessary in order to detect rule violations for example for tournament play. This project describes an automatic referee using sensors on a regular soccer table to detect rule violations. The gap between noisy sensor data and the high-level concept of a kick is bridged by using naive Bayes classifiers for kick detection. Input to the classifiers are the coordinates of the ball relative to the kicking figure, modelled as Gaussian distributions. The classifier is trained offline using supervised learning. In the experiments, all rule violations were detected online. The implementation proved its usefulness by being used in regular games. Future work on segmenting table soccer games or sequence learning can benefit from the findings of this project by classifying game situations with the methods described here.
Complete Report (34 pages, 0.9 MB)