Overview of current trends in aerospace image processing and pattern recognition

Abstract

This article presents a comparative analysis of methods for water body detection on multichannel aerial images. The main problems that arise when identifying water bodies of various types in images obtained from satellite remote sensing systems are considered. The article describes and compares various methods used for water body detection. The main methods include spectral water indices (NDWI, MNDWI, AWEI), image classification methods (zero threshold method, Otsu method, k-nearest neighbors method) and modern ma-chine learning approaches. Thus, the article is devoted to a topical topic in the field of processing and analyzing multichannel aerial images for water body detection. It contains useful information for re-searchers working in the field of remote sensing and can serve as a basis for selecting the op-timal methods for classifying water bodies depending on specific conditions and tasks.