Application of Statistical Models of Image Texture and Physical Parameters of Clouds for Their Classification on MODIS Satellite Images
- Autores: Skorokhodov A.1, Astafurov V.1,2, Evsutkin T.1
-
Afiliações:
- Institute of Atmospheric Optics, Siberian Branch, Russian Academy of Sciences
- Tomsk State University of Control Systems and Radioelectronics
- Edição: Volume 55, Nº 9 (2019)
- Páginas: 1053-1064
- Seção: Methods and Tools for Space Data Processing and Interpretation
- URL: https://journals.rcsi.science/0001-4338/article/view/148793
- DOI: https://doi.org/10.1134/S0001433819090482
- ID: 148793
Citar
Resumo
Modifications of algorithms for the classification of single-layer, vertical development clouds, and multilayer clouds based on a probabilistic neural network and a neuro-fuzzy classifier are proposed. Clouds are classified into 16 types according to the meteorological standard, including the combined subtypes of stratus, altocumulus, cirrus, and cirrostratus clouds. The article uses a description of clouds based on information about the texture of their images on satellite images from MODIS and its products with data on the physical parameters of clouds. The structure of classification algorithms is described. The results of the use of statistical models of image texture and physical parameters of clouds for initializing membership functions for a neural-fuzzy classifier are presented. Systems of effective classification characteristics for different classification algorithms are formed based on the GRAD modified truncated search method. The recognition results of single-layer, vertical development clouds, and multilayer clouds based on the corresponding test samples and full-size sets of MODIS satellite data with different spatial resolution are discussed.
Sobre autores
A. Skorokhodov
Institute of Atmospheric Optics, Siberian Branch, Russian Academy of Sciences
Autor responsável pela correspondência
Email: vazime@yandex.ru
Rússia, Tomsk
V. Astafurov
Institute of Atmospheric Optics, Siberian Branch, Russian Academy of Sciences; Tomsk State University of Control Systems and Radioelectronics
Email: vazime@yandex.ru
Rússia, Tomsk; Tomsk
T. Evsutkin
Institute of Atmospheric Optics, Siberian Branch, Russian Academy of Sciences
Email: vazime@yandex.ru
Rússia, Tomsk