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 B6a
页码：159-164
出版社：Copernicus Publications
摘要：Crop area estimates are crucial for the Common Agricultural Policy of the European Union to manage future intervention on stocks and export policies. The requirement is for early and accurate information, provided in real time and at the lowest possible cost. On this base a study was started by the Joint Research Centre (JRC) – Ispra of the EU Commission, to assess the feasibility of satellite Synthetic Aperture Radar (SAR) imagery in providing such estimates. The study area was located in the Tuscany region of Italy, and the investigation concentrated on a classification procedure linked to SAR data properties The study tested a rule-base classification capable of assigning class labels without employing training samples. These "rules" relied on crop-specific temporal sequences of cultivation practices identified by changes in backscattering. The proposed classifier provided a level of accuracy well below requirements though of some relevance for a set of 5 crop groups (winter cereals, spring crops, trees, pasture and forage crops). The project produced however a number of useful considerations on the operational use of SAR data fro land use mapping
关键词：SAR; Crop Mapping; Data Integration; Rule Base Classification; Forward Chaining
