Modeling and Recognition of Video Events with Fuzzy Semantic Petri Nets

This paper addresses the problem of modeling and automated recognition of complex behavior patterns in video sequences. We introduce a new concept of Fuzzy Semantic Petri Nets (FSPN) and discuss their application to recognition of video events. FSPN are Petri nets coupled with an underlying fuzzy ontology. The ontology stores assertions (facts) concerning classification of objects and detected relations. Fuzzy predicates querying the ontology content are used as guards of transitions in FSPN. Tokens carry information on objects participating in a scenario and are equipped with weights indicating likelihood of their assignment to places. In turn, the places correspond to scenario steps. The Petri net structure is obtained by translating a Linear Temporal Logic formula specifying a scenario in a human-readable form. We describe a prototype detection system consisting of an FSPN interpreter, the fuzzy ontology and a set of predicate evaluators. Initial tests yielding promising results are reported.