摘要：In this paper we propose and evaluate different mathematical parameters extracted from the experimental semivariogram for land use/land cover classification using high-resolution images and cadastral mapping limits for the definition of the objects of analysis. First, we describe the process of calculating the semivariogram from the gray level values in an image object. In order to optimize the computation time we present two pixel selection techniques that preserve the original shape of the semivariogram. Several parameters are then extracted from the semivariogram. Finally, we use various statistical techniques to select the most discriminant parameters. Last section shows the results obtained using aerial digital images of an agricultural area on the Mediterranean coast of Spain. The study of the practical application presented in this paper facilitates the understanding of the relationship between the behaviour of the experimental semivariogram and the variability of the intensity values in a digital image. In order to follow the development of this work, the reader should know some basis of classification methods and digital image processing techniques.
其他摘要：In this paper we propose and evaluate different mathematical parameters extracted from the experimental semivariogram for land use/land cover classification using high-resolution images and cadastral mapping limits for the definition of the objects of analysis. First, we describe the process of calculating the semivariogram from the gray level values in an image object. In order to optimize the computation time we present two pixel selection techniques that preserve the original shape of the semivariogram. Several parameters are then extracted from the semivariogram. Finally, we use various statistical techniques to select the most discriminant parameters. Last section shows the results obtained using aerial digital images of an agricultural area on the Mediterranean coast of Spain. The study of the practical application presented in this paper facilitates the understanding of the relationship between the behaviour of the experimental semivariogram and the variability of the intensity values in a digital image. In order to follow the development of this work, the reader should know some basis of classification methods and digital image processing techniques.
