Improved land use classification by means of a digital topographic database and integrated knowledge processing

The central idea of this new approach is the investigation and use of synergy effects between satellite image analysis and a digital topographic database. The use of such topographic databases can improve and automate satellite image analysis, not only for a knowledge based feature extraction, but also for the following process of semantic modelling of topographic objects inside the scene. The result is an actual semantic description of the scene content. Because of the relatively poor geometric resolution of common satellite sensors this project concentrates on main area-based land use classes like 'settlement', 'forest', 'water' and 'agriculture'.