Using Ontologies in a Cognitive-Grounded System: Automatic Action Recognition in Video-Surveillance

This article presents an integrated cognitive system for automatic video surveillance: in particular, we focus on the task of classifying the actions occurring in a scene. For this purpose, we developed a semantic infrastructure on top of a hybrid computational ontology of actions. The article outlines the core features of this infrastructure, illustrating how the processing mechanisms of the cognitive system benefit from knowledge capabilities in fulfilling the recognition goal. Ultimately, the paper shows that ontologies can enhance a cognitive architecture’s functionalities, allowing for high-level performance in complex task execution.