Integrated Ontologies for Spatial Scene Descriptions

Abstract

Scene descriptions are typically expressed in natural language texts and are integrated within Web pages, books, newspapers, and other means of content dissemination. The capabilities of such means can be enhanced to support automated content processing and communication between people or machines by allowing the scene contents to be extracted and expressed in ontologies, a formal syntax rich in semantics interpretable by both people and machines. Ontologies enable more effective querying, reasoning, and general use of content and allow for standardizing the quality and delivery of information across communicating information sources. Ontologies are defined using the well-established standards of the Semantic Web for expressing scene descriptions in application fields such as Geographic Information Systems, medicine, and the World Wide Web (WWW). Ontologies are not only suitable for describing static scenes with static objects (e.g., in photographs) but also enable representation of dynamic events with objects and properties changing in time (e.g., moving objects in a video). Representation of both static and dynamic scenes by ontologies, as well as querying and reasoning over static and dynamic ontologies are important issues for further research. These are exactly the problems this chapter is dealing with.