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 B3b
页码：115-118
出版社：Copernicus Publications
摘要：In Digital Terrain Models (DTM) interpolation is actually a surface fitting problem. For the estimation of heights of points with known X-Y coordinates there are many interpolation methods. Besides, there are various works about the determination of DTM accuracy. The aim of this study is to develop an Artificial Neural Network (ANN) method as an alternative to other common methods. The ANN model having Multi Layer Perception structure is programmed under Matlab. This ANN method and selected seven interpolation methods are tested in a test area and the result are compared. In terms of accuracy, the results show that ANN does not deliver the best results, but seems as an alternative interpolation method
