Ontology for Semantic Integration in a Cognitive Surveillance System

The recent growing of interest in sophisticated intelligent systems dealing with advanced interfaces, as in the case of Cognitive Vision Systems (CVS), motivates the apparition of ad-hoc stages designed for the integration of multiple domains of semantic knowledge. This paper proposes a novel ontology as a suitable mechanism to restrict and integrate high-level semantics for Human Sequence Evaluation (HSE), which incorporates multilingual capabilities and multipurpose end-user interfaces. The main contributions of this paper are the conception of a neutral semantic layer formed by High-Level Semantic Predicates (HLSP), which allow to link semantics representations from vision and linguistic domains; and the use of situations instead of verbs as the basic elements for an ontological categorization of interpreted occurrences. In this particular approach, the domain has been restricted to the field of human behaviors in outdoor surveilled scenarios, involving interactions among pedestrians, static objects, and vehicular traffic.