植生指標とテクスチャを併用したLandsat TM画像からの畑領域抽出手法

抄録

Land cover and use classification on a huge scale, e. g. national or continental scale, has become more and more important because environmental researches need land cover and use data on such scales. We developed a crop field extraction method, which is one of the steps in our land cover classification system for a huge area. Firstly, a crop field model is defined to characterize“crop field”in terms of NDVI value and textual information. Textual information is represented by the density of straight lines which are extracted by wavelet transform. Secondly, candidates of NDVI threshold value are determined by“scale-space filtering”method. The most appropriate threshold value among the candidates is determined by evaluating the line density of the area extracted by the threshold value according to the crop field model. The crop field is extracted by applying level slicing to Landsat TM image with the threshold value determined above. The experiment demonstrates that the extracted area by this method coincides very well with the one extracted by visual interpretation.