An Ontology for Video Event Representation

Representation and recognition of events in a video is important for a number of tasks such as video surveillance, video browsing and content based video indexing. This paper describes the results of a "Challenge Project on Video Event Taxonomy" sponsored by the Advanced Research and Development Activity (ARDA) of the U.S. Government in the summer and fall of 2003. The project brought together more than 30 researchers in computer vision and knowledge representation and representatives of the user community. It resulted in the development of a formal language for describing an ontology of events, which we call VERL (Video Event Representation Language) and a companion language called VEML (Video Event Markup Language) to annotate instances of the events described in VERL. This paper provides a summary of VERL and VEML as well as the considerations associated with the specific design choices.