Time Interval based Modelling and Classification of Events in Soccer Video

machine, soccer Multimodal indexing of events in video documents poses problems with respect to representation, inclusion of contextual information, and synchronization of the heterogeneous information sources involved. In this paper we propose to model events in multimodal video by means of time interval relations, to tackle aforementioned problems. Our approach exploits the powerful properties of statistical classifiers, like the Maximum Entropy and Support Vector Machine classifiers. To demonstrate the viability of our approach for event classification in multimodal video, an evaluation was performed on the domain of soccer broadcasts. It was found that the amount of video a user has to watch in order to see almost all highlights can be reduced considerably. Furthermore, we found that a Support Vector Machine performs better than a Maximum Entropy classifier.