Our work is concerned with the design of a knowledge-based system for recognizing agricultural landscape models on land-use maps. Landscape models are defined as sets of spatial structures and spatial relations. This paper focuses on the representation of topological relations inside an object-based representation system. In this system, relations are represented by objects with their own properties. We propose to define two types of properties: the first ones are concerned with relations as concepts while the second are concerned with relations as links between concepts. In order to represent the second type of properties, we have defined facets that are inspired from the constructors of description logics. We describe these facets and how they are used for classifying spatial structures and relations on land-use maps. The paper ends with a discussion on the present work and related work in qualitative spatial reasoning.

Object-based knowledge representation, topological relations, classification, relation reification, landscape analysis