Multimedia reasoning, which is suitable for, among others, multimedia content analysis and high-level video scene interpretation, relies on the formal and comprehensive conceptualization of the represented knowledge domain. However, most multimedia ontologies are not exhaustive in terms of role definitions, and do not incorporate complex role inclusions and role interdependencies. In fact, most multimedia ontologies do not have a role box at all, and implement only a basic subset of the available logical constructors. Consequently, their application in multimedia reasoning is limited.
The VidOnt OWL 2 ontology is a description logic-based knowledge representation which can serve as the basis for multimedia content analysis, event detection, high-level video scene interpretation, and constructing high-level media descriptors. In contrast to other multimedia ontologies, VidOnt exploits all constructs of SROIQ(D), one of the most expressive decidable description logics, and beyond the Tbox and ABox axioms defining its knowledge base, it provides a role box (RBox) and a DL-safe ruleset for complex reasoning tasks.
The inferred axioms are automatically generated with full certainty, which makes the combination of complex role inclusion axioms and DL-safe rules suitable for big data implementations, video cataloging to automatically generate new axioms through user or programmatic queries, and knowledge discovery, such as to identify those factors from medical videos that can together indicate a disease.