Analysis and interpretation of changes in aerial images: knowledge representation and spatial reasoning

In this paper we present a logic-based approach to the interpretation of changes in aerial images with respect to reference information extracted from a map. We propose using a KL- ONE-like description logic, first, for representing knowledge about types of objects and types of possible changes, and second, as a central reasoning component of an interpretation system. This approach can be applied to the task of updating map data in geographic information systems.