Ontological representation of context knowledge for visual data fusion

Abstract

Context knowledge is essential to achieve successful information fusion, especially at high JDL levels. Context can be used to interpret the perceived situation, which is required for accurate assessment. Both types of knowledge, contextual and perceptual, can be represented with formal languages such as ontologies, which support the creation of readable representations and reasoning with them. In this paper, we present an ontology-based model compliant with JDL to represent knowledge in cognitive visual data fusion systems. We depict the use of the model with an example on surveillance. We show that such a model promotes system extensibility and facilitates the incorporation of humans in the fusion loop.