On Scene Interpretation with Description Logics

We examine the possible use of Description Logics as a knowledge representation and reasoning system for high-level scene interpretation. It is shown that aggregates composed of multiple parts and constrained primarily by temporal and spatial relations can be used to represent high-level concepts such as object configurations, occurrences, events and episodes. Scene interpretation is modelled as a stepwise process which exploits the taxonomical and compositional relations between aggregate concepts while incorporating visual evidence and contextual information. It is shown that aggregates can be represented by a Description Logic ALCF(D) which provides feature chains and a concrete domain extension for quantitative temporal and spatial constraints. Reasoning services of the DL system can be used as building blocks for the interpretation process, but additional information is required to generate preferred interpretations. A probabilistic model is sketched which can be integrated with the knowledge-based framework