Statistical model of cirrus cloud textural features based on MODIS satellite images
V.G. Astafurov1,2, T.V. Evsyutkin1, K.V. Kuriyanovich1, A.V. Skorokhodov1
1V.E. Zuev Institute of Atmospheric Optics of Siberian Branch of the Russian Academy of Science, 1, Academician Zuev square, Tomsk, 634021, Russia
2Tomsk State University of Control Systems and Radioelectronics, 40 Lenina Prospect, Tomsk, Russia 634050
Keywords: cirrus clouds, textural features, statistical model, classification, satellite data
Abstract
A set of informative textural features is formed for various cirrus cloud patterns presented in MODIS satellite images with 250-m resolution. To describe the texture, the following methods are applied: Gray-Level Co-occurrences Matrix, Gray-Level Difference Vector, and Sum and Difference Histograms. Laws are determined that describe textural features’ fluctuations, and assessments of their parameters are presented as well. Results of cirrus cloud subtype classification using neural network technologies are presented and discussed.
|
