Ontology-based forensic event detection using inference rules

Following the exponential deployment of surveillance systems across a wide-spread region of geographic locations, detection and representation of events has become a critical element in automated surveillance systems. In this paper, we focus on the high-level event recognition in the forensic domain. We present an extensive ontology framework for representing complex semantic events. To represent the richer relationships, which is not supported by the standard ontology semantics, event (activity) recognition is further augmented with rules. The proposed ontology builds on DOLCE ontology and relies on the linguistic and cognitive modelling of philosophical knowledge to achieve interoperability between proprietary surveillance systems. The expressiveness of the proposed ontology framework is described in the context of London Riots which took place in 2011.