Automated generation of visual simulation databases using remote sensing and GIS

This paper reports on the development of a strategy to generate databases used for real-time interactive landscape visualization. The database construction from real world data is intended to be as automated as possible. The primary sources of information are remote sensing imagery recorded by Landsat´s Thematic Mapper (TM) and digital elevation models (DEM). Additional datasets (traffic networks and buildings) are added to extend the database. In a first step the TM images are geocoded and then segmented into areas of different land coverage. During the visual simulation highly detailed photo textures are applied onto the terrain based on the classification results to increase the apparent amount of detail. The data processing and integration is carried out using custom image processing and geographic information systems (GIS) software. Finally, a sample visual simulation application is implemented. Emphasis is put on practical implementation to test the feasibility of the approach as a whole