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：2008
卷号：XXXVII Part B2
页码：869-874
出版社：Copernicus Publications
摘要：In the remote sensing data not only have radiation error and geometry error, need geometry correction and radiometric correction, but most of them also have "same object different spectrum"and"same spectrum different object" phenomena. The report of Digital Orthophoto Map quality is subjective and limited,so it confine the application level of remote sensing imagery. some of which may seriously distort the reliability of products .Thereby, Uncertainties in Remote Sensing Information problem, receive more and moe broad attention. Some important international academic institutions or organizations hold the Remote Sensing Information problem as the 21st century's major research topic.In this paper use the theory of rough sets appraise remote sensing information At the same time it also compared with other uncertainties remote sensing date mothed. In the classical fashions, e.g. error matrix and kappa coefficient, the performance of the classification models is estimated directly on the training date.Whereas it is actually not appropriate. The error matrix based on the training date set can not be regarded as the measurement of overall accuracy of classification models, and these models performance need to be evaluated on "out-of-sample-date" date that have not been used in constructing the modela. ProPose a new mehtod of diseretization of eontinuous attributes based on dynamic-layer-cluster.A unified framework of the rough set theory to deal with discrete and continuouse attributes is suggested
