Automatic veri cation of GIS data using high resolution multispectral data

Geographic information systems (GIS) are dependent on accurate and up-to-date data sets. The manual revision of GIS data is very cost and time consuming. On the other hand more and more high resolution satellite systems are under development and will be operational soon-thus highly resolution remote sensing data will be available. In this paper a fully automated approach for veriication of GIS objects using remote sensing data is presented. In a rst step a supervised maximum likelihood classiication is performed. It is necessary that the training areas for the supervised classiication are derived automatically in order to develop a fully automated approach. The already existing GIS data are used to compute a pixel mask (which represent the shade of the training areas) for each object class. In order to nd inconsistencies between the GIS data and the remote sensing data the result of the classiication has to be matched with the GIS data. It is shown that diierent approaches are needed when dealing with area objects and with line objects. This paper focuses on the matching of area objects. The approach was tested with ATKIS data sets and DPA high resolution remote sensing data. ATKIS is the German topographic cartographic spatial database and DPA (Digital Photogrammetric Assembly) is an optical airborne imaging system for real time data collection. This paper shows the results of the automatic veriication of ATKIS objects represented in DPA data.