Open AccessMULTIDIMENSIONAL STATISTICAL MODEL FOR DETECTING OIL POLLUTION SITES BASED ON SATELLITE IMAGERY
Author(s) -
Alovsat Shura Guliyev,
T. A. Khlebnikova
Publication year - 2021
Publication title -
interèkspo geo-sibirʹ
Language(s) - English
Resource type - Journals
ISSN - 2618-981X
DOI - 10.33764/2618-981x-2021-4-1-11-16
Subject(s) - oil spill , remote sensing , synthetic aperture radar , satellite , computer science , satellite imagery , submarine pipeline , statistical model , image resolution , oil pollution , environmental science , geology , computer vision , artificial intelligence , petroleum engineering , engineering , geotechnical engineering , aerospace engineering , environmental engineering
The article considers an algorithm for determining the statistical model from several inhomogeneous images of the Earth's surface obtained by different sensors (optoelectronic scanning device, synthetic aperture radar (SAR)) over the sea areas. The object of the study are the methods of remote sensing of the Earth used for detection and mapping of oil spills. The aim of the research was to perform testing for a possible variation of the statistical model inside a non-uniform sliding window based on a semi-automatic approach. The proposed algorithm makes it possible to determine the spatial extent of oil production sites and oil pollution in offshore waters using multi-time RSA data and a multi-zone combined image with a spatial resolution of 10 m. First, homogeneous regions are analyzed in the image, and then the model of the analysis zone is expanded to the more general case of inhomogeneous regions that are observed in the analysis windows.