Development of Intelligent Algorithms for Interpretation of Images of the Remote Image of the Earth

The paper considers the problems of developing intelligent algorithms for interpreting images of a remote image of the earth, since the automatic interpretation of these images becomes relevant. In this context, reference datasets serve as important prerequisites for developing and testing intelligent interpretation algorithms. The paper discusses the problem of how to efficiently prepare a suitable reference dataset for the interpretation of remote sensing images. The paper discusses the problem of classification of remote sensing images using the Convolutional Neural Network.