文章基本信息

标题：An object-based classification procedure for the derivation of broad land cover classes using both optical and SAR data
本地全文：下载
作者：T. RIEDEL ; C. THIEL ; C. SCHMULLIUS 等
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：2006
卷号：XXXVI-4/C42
出版社：Copernicus Publications
摘要：The availability of up-to-date and reliable land cover maps is of great importance for many earth science applications. For the generation of operational and transferable land cover products the development of semi- and fully-automated classification procedures is essential. The Enviland project deals with the development of novel approaches for the generation of land cover products using both optical and SAR data. In a first step an automatic classification scheme for the delineation of broad land cover categories such as water, forest, urban areas and agricultural fields / grassland will be designed. This paper presents the first results of the sub-project "scale integration". The study area is located in northern Thuringia, Germany, including mainly forested regions like the eastern part of the low mountain range Harz as well as intensively used agricultural areas. From April to December 2005 optical and SAR data were acquired continuously over the test site building up a comprehensive time series (e.g. 4 Landsat-5 TM, 17 Envisat ASAR APP and 10 ERS-2 scenes). In this paper an object-based hierarchical classification scheme for the derivation of broad land cover classes using both optical and SAR data is presented. The segmentation of the EO-data was done using the eCognition software. The thresholds of the decision tree are based on reflectance values, the backscattering coefficient and texture information. By the integration of textural features in the classification process the classification accuracy could be improved significantly, especially in the context of urban areas. In this study the power of the grey level dependency matrix – rarely used in the field of remote sensing – is demonstrated
关键词：SAR; optical; synergy; land cover