VidOnt: a core reference ontology for reasoning over video scenes

Abstract

The conceptualization of domains depicted in videos is a necessary, but not sufficient requirement for reasoning-based high-level scene interpretation, which requires the formal representation of the timeline structure, the moving regions of interest, and video production standards, facilities, and procedures as well. Multimedia ontologies, including the very few video ontologies, however, are not exhaustive in terms of concept coverage, redefine terms against Semantic Web best practices, are not aligned with standards, and do not define complex roles and role interdependencies. Because most multimedia ontologies implement only a minimal subset of the mathematical constructors of OWL, and define a TBox and an ABox, but not an RBox, they do not support complex inferencing. This paper describes a formally grounded core reference ontology for video representation, which addresses many of these issues and limitations.

Keywords

• Video ontology
• scene interpretation
• video understanding
• MPEG-7
• spatiotemporal annotation
• content-based video retrieval