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：In general, built-up areas or populated places are significantly changing within the revision interval of a GIS (Geographic InformationSystem) or map. In this paper we present a method by means of which built-up areas are extracted from panchromatic satellite images ofSPOT and IRS-1C and which makes use of the available information about built-up areas in the GIS. The method has been developed forsmall-scale maps or GIS where built-up areas are represented by their outline stored as a closed polygon. The texture of built-up areasin satellite images is characterized by a high spatial density of very short linear features. This density is used to classify built-up andnon-built-up areas. The decision is made by a threshold estimated from training sites which are derived from the built-up areas stored inthe GIS. The suitability of the method is demonstrated using SPOT and IRS-1C data as examples
关键词：GIS Update; Small-Scale; Image Analysis; Texture; Linear Feature; Point Detection
