A brief description and the results of experimental testing of a technique for automated processing and analyzing multispectral satellite images of medium and high spatial resolution with the aim of detecting and assessing the dynamics of large logging areas in the territory of the Republic of Kazakhstan are presented. More than 50 large logging areas of about 100 hectares were detected in the selected monitoring site (district of Kokshetau, Akmola territory).
The paper considers an algorithm for automated classification of mobile small size objects on multispectral satellite images of submeter spatial resolution using radiometric and geometric features. It ensures recognizing the desired classes of objects with high accuracy regardless of their orientation in the image. The geometric features of the objects classified in the binary image included the area of the object, the lengths of the principal and auxiliary axes of inertia, the eccentricity of the ellipse with the main moments of inertia, the area of a convex polygon described near the object, the equivalent diameter of a circle with the same area, and the convexity coefficient.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.