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：878-883
出版社：Copernicus Publications
摘要：For past many years, many researchers have devotedconsiderable effort to the problem of imagerepresentation. However, no recent study has beenundertaken for an interpretation of remotely sensedimage based on the combination of multiformrepresentations under conditions where a computersystem can interpret an image by incorporating multi- information overlap analysis in the traditionalrepresentation of image understanding. In this paper,we describe an multilevel representation tree composedof synthetic land unit map ,land unit relatability list,complexes labeling, correlation list and region relationgraphs. This representation tree allows one to interpretimage in terms of remotely sensed image and nonremotelysensed digital maps that may providegeometric, topological, overlapping and attributiveinformation in a form suitable for imageinterpretation. We present an interpretation forremotely sensed image by using multilevelrepresentation tree and give also a number ofexperimental results.
关键词：Representation; Interpretation;Multilevel representation tree; Synthetic land unit;map; Complexes labeling; Correlation list
