Dynamic description of event on desktop environment based on Cognitive Ontology

Automatic detection and description of events, particularly human behavior, is one of the most challenging issues, since event interpretation is highly dependent on the target of attention, which is not uniquely specified. To tackle this problem, we propose the concept of a ldquocognitive ontologyrdquo as a framework for a system that can automatically decide the attention focus and describe the events. A cognitive ontology is structured with conceptual units which are Entities and Relations, and these units enable robot endogenous attention fixation and jumps based on a networked Cognitive Ontology. To construct a Cognitive Ontology structure, we used a Bayesian network for the relationships of an Ontological network. We evaluate the performance of a probabilistic event description by visual information using Cognitive Ontology in an experimental event description of a desktop situation.