Video event modelling and association rule mining in multimedia surveillance systems

Event representation models provide a framework in which we can reason about events so as to interpret the collective behaviour of objects over time and space domains. Many are context-specific and lack flexibility when faced with unstructured video. This paper proposes a comprehensive event modelling framework for multimedia surveillance systems. An event detection model incorporates multimedia strings and a new predicate set for describing more complex event scenarios. Event classification performance is evaluated on benchmarked datasets.