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：2002
卷号：XXXIV Part 4
出版社：Copernicus Publications
摘要：While the integration of data has been performed on various levels for quite a time, the logical consequence - the integration of methods - has been rather neglected especially in the context of the analysis of remotely sensed data. On the other hand the present way of combining methods is partially responsible for unsatisfying results which have to be noticed for instance for object recognition processes. Hence, goal of the paper is to demonstrate the respective drawbacks of currently applied linear sequence approaches, to present general design concepts for alternative method networks, and to describe a corresponding implementation for the task of object recognition based on data of Digital Surface Models
关键词：method integration; system architecture; object recognition; DEM/DTM/DSM; blunder analysis; normalization
