Control of Scene Reconstruction Using Explicit Knowledge

Applications such as landscape planing, environmental monitoring, andflight and driving simulators have a high demandfor realistic landscape models. Quantity, precision and the type of models ask for methods which automate the model generation by evaluation of remote sensing data. The presented modelling system AIDA tackles the demandfor eficient representation and high realism by integrating a prion ’ knowledge about the appearance of the objects in the scene to derive object specific constraints for JD-reconstruction. This requires an image interpretation to assign a meaning to the objects in the scene. For explicit representation of the declarative andproceduralknowledge a problem-independentformalism based on semantic nets and rules is used. It provides both a data-driven and model-driven control strategy.