摘要：Supervised classification of remote sensing imagery implies usage of a priori knowledge of analysed area of interest for proper selection of land cover classes’ samples. Spectral and geometric properties of the satellite image were taken into account by parameters of the multiresolution segmentation algorithm that has been used to divide the selected subset of the scene into homogeneous groups of pixels. Such image segments were used as land cover samples for supervised classification. Accuracy assessment was performed by means of error matrix based on stratified random samples.
关键词：land cover; satellite images; method of supervised classification; image segmentation; error matrix; V-I-S model
