期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：1998
卷号：XXXII Part 4
出版社：Copernicus Publications
摘要：Geographic information systems (GIS) are dependent on accurate and up-to-date data sets. The manual revision of GISdata is very cost and time consuming. On the other hand more and more high resolution satellite systems are underdevelopment and will be operational soon - thus high resolution remote sensing data will be available. In this paper a fullyautomated approach for verification of GIS objects using remote sensing data is presented. In a first step a supervisedmaximum likelihood classification is performed. It is necessary that the training areas for the supervised classification arederived automatically in order to develop a fully automated approach. The already existing GIS data are used to computepixel masks (which represent the training areas) for each object class. In order to find inconsistencies between the GISdata and the remote sensing data the result of the classification has to be matched with the GIS data. It is shown thatdifferent approaches are needed when dealing either with area objects or with line objects. Examples on both approachesare presented. The automatic verification was tested with ATKIS data sets and DPA high resolution remotesensing 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 automaticverification of ATKIS objects represented in DPA data
