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：2000
卷号：XXXIII Part B2
页码：287-294
出版社：Copernicus Publications
摘要：This paper introduces a fully automatic approach for the registration of satellite imagery by matching extracted image segments against the corresponding objects of an existing a GIS data base. Within the study SPOT imagery is exempla- rily applied, whereas the topographic data base is provided by the German ATKIS. Since neither lines nor points allow for the determination of the complete transformation for each pair of corresponding objects, the image-to-map- transformation is based on corresponding regions, which are defined by polygons. The selected GIS objects are matched to the extracted image objects in a three phase process. In the first phase, a coarse global affine transformation between satellite image and vector map is determined. The second phase refines this global transformation by applying a super- vised segmentation using seed regions, which are generated based on the results of the first phase. In the third phase individual transformations between corresponding objects are computed. After this step, ground control points at the boundaries of the corresponding polygons are available, which can be used as input for a standard aerial triangulation process
