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 B7
页码:769-776
出版社:Copernicus Publications
摘要:Geographical Information System and Remote Sensing are tools which integrated can perform different environmental analysis. The Netherlands ITC (Institute for Aerospace Survey and Earth Sciences) developed in 1984 on Integrated Land and Water Information System (ILWIS), that combines raster (satellite image and aerial photo analysis), vector and thematic data operations in one comprehensive integrated Remote Sensing –GIS software. Since July 1 2007, ILWIS 3.4 has been granted open source status and is currently maintained by the open source community 52North, a no-profit organization under German legislation. In this research I developed in the ILWIS environment new tools to perform an unsupervised Remote Sensing classification on a set of TM Landsat images to generate thematic maps for glacier analysis. The work starts after having tested some algorithms, inside the software, related to the supervised classification, which pointed out the potentiality of its performances for the computer-assisted interpretation of remotely sensed data and made in evidence dedicated spatial analysis for the glacier state monitoring. To integrate these procedures with other suitable classifiers I used the form of the script language to implement the K-means and the Fuzzy K-means algorithms with the aim to define landform elements. Finally I compared the results, coming from the different performances, by means some accuracy parameters