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：2003
卷号：XXXIV-3/W8
出版社：Copernicus Publications
摘要：Digital spatial data are subject to temporal changes. The common approach to verify and update the data is to superimpose the dat a with up-to-date orthophotos and check the correctness interactively. This is a very time consuming and expensive process. We propos e a method for the automatic quality surveillance of GIS data, in particular in respect to changes of settlement and industrial areas. Thes e classes correspond to the classes defined for the German ATKIS R geodata. In this paper the up-to-dateness of ATKIS is checked by use of a high resolution color aerial image of a scene near Hannover. The analysis uses the knowledge-based system G EO AIDA , which allows an intelligent, clearly structured, and .exible control of a scene interpretation by utilizing a semantic scene description . G EO AIDA is extended to use a state transition graph that models possible expected temporal transitions in the scene. The system produces a hierarchic, pictorial description of the results while the structural context of the identified objects including the associated attributes is preserved in a graph. The results of a quality surveillance procedure in the examined GIS data are illustrated
