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：1992
卷号：XXIX Part B3
页码：578-585
出版社：Copernicus Publications
摘要：Present results of map interpretation systems still requiresignificant manual interaction effort. This is mainlycaused by a lack of high level knowledge in the systems.In this paper we introduce a multi-level model for alarge-scale map as the key to improved and robust automaticmap interpretation. The levels of the model arecalled semantic objects, graphics and text, image graphand image. Objects, operations to be performed on theobjects and relations between the objects are presentedfor each level.Mixed bottom-up and top-down reasoning is performedby instantiating the concepts of a semantic network builtup from the semantic objects, the graphics and text andthe image graph levels. The interpretation uses relationson attributed arcs and nodes as well as template matchingon the image.First results for the interpretation of a Bavarian cadastralmap of scale 1 : 1000 are presented.
关键词：automatic map interpretation; model based;interpretation; semantic network; top-down and bottom-;up processing
