A MODEL TO SUPPORT THE INTEGRATION OF IMAGE UNDERSTANDING TECHNIQUES WITHIN A GIS

Traditionally, geographic information systems (GIS) have used data gen erated from remote sensing, but only after the data have been preproce ssed in some way to provide a suitable classification. This leads to s everal weaknesses; the resulting framework is inflexible and cannot su pport multiple interpretations of the same area. A new model for a GIS is introduced that includes a set of image understanding methods, and expert knowledge governing the application of these methods. The meth ods employed are chosen automatically to best emphasize the types of f eatures (rivers, fields, forests, etc.) that the user is currently inv estigating, and the type of imagery available. An implementation of th e model is described along with details of the knowledge structures an d image processing methods used. Examples are included to show the res ulting adaptive nature of image interpretation and subsequent inclusio n of feature descriptions into the GIS.