All
 
|
 
 


Application of Statistical Models of the Image Textures and Physical Parameters of Clouds for Their Classifi cation on Satellite Imagery MODIS
 
PIIS020596140002355-1-1
DOI10.31857/S020596140002355-1
Publication type Article
Status Published
Authors
A. Skorokhodov 
Affiliation: Institute of Atmospheric Optics V.E. Zueva Siberian Branch of the Russian Academy of Sciences
Address: Russian Federation
V. Astafurov
Affiliation: Institute of Atmospheric Optics V.E. Zueva Siberian Branch of the Russian Academy of Sciences
Address: Russian Federation
T. Evsyutkin
Affiliation: Tomsk State University of Control Systems and Radioelectronics
Address: Russian Federation
Journal nameIssledovanie Zemli iz kosmosa
EditionIssue 4
Pages43-58
Abstract

Modifi cations of algorithms for the classifi cation of single-layer, vertical development and multi-layer clouds based on the probabilistic neural network and the neuro-fuzzy classifi er are proposed. Clouds are classifi ed into 16 types according to the meteorological standard including the combined subtypes of stratus, altocumulus, cirrus and cirrostratus clouds. The paper uses a cloud descriptions based on information on the texture on MODIS satellite imagery and its products containing data on the physical parameters of cloud cover. The structure of the classifi cation algorithms is described. The results of the use of statistical models of the image textures and physical parameters of clouds to initialize the membership functions in neural-fuzzy classifi er are presented. Formation of eff ective classifi cation characteristics systems for diff erent algorithms was carried out on the basis of the GRAD modifi ed method of truncated search. The recognition results of single-layer, vertical development and multi-layered cloud types on the basis of the corresponding test samples and full-size sets of MODIS satellite data having diff erent spatial resolution are discussed.

Keywordsinformativeness, classifi cation, fuzzy-logic methods, neural network, clouds, satellite data, statistical model, texture features, physical parameters
AcknowledgmentThis work was supported by the Russian Foundation for Basic Research in the framework of the research project No. 16-37-60019 mol_a_dk.
Received22.12.2018
Publication date22.12.2018
Cite   Download pdf To download PDF you should sign in
Размещенный ниже текст является ознакомительной версией и может не соответствовать печатной

views: 1339

Readers community rating: votes 0 

1. Abramovits M., Stigan I. Spravochnik po spetsial'nym funktsiyam / Per. s angl. V.A. Ditkina, L.N. Karmazinoj. M.: Nauka, 832 s.
2. Astafurov V.G., Skorokhodov A.V. Klassifikatsiya mnogoyarusnoj oblachnosti po dannym MODIS s ispol'zovaniem tekhnologii nejronnykh setej i metodov nechetkoj logiki // Sovr. probl. dist. zondir. Zemli iz kosmosa. 2015. T. 12. № 6. S. 162–173.
3. Astafurov V.G., Skorokhodov A.V. Formirovanie sistemy informativnykh klassifikatsionnykh kharakteristik pri reshenii zadachi klassifikatsii oblachnosti po sputnikovym dannym MODIS // Tr. SPIIRAN. 2017. T. 53. № 4. S. 118–139.
4. Astafurov V.G., Skorokhodov A.V. Statisticheskaya model' fizicheskikh parametrov oblachnosti na osnove tematicheskikh produktov MODIS // Issled. Zemli iz kosmosa. 2017. № 5. S. 66–81.
5. Bespalov D.P., Devyatkin A.M., Dovgalyuk Yu.A., Kondratyuk V.I., Kuleshov Yu.V., Svetlova T.P., Suvorov S.S., Timofeev V.I. Atlas oblakov. SPb.: D’ART, 2011. 248 c.
6. Bondur V.G., Arzhenenko N.I. Klassifikatsiya oblachnykh form po prostranstvennym spektram izobrazhenij // Optika atmosfery i okeana. 1988. № 11. S. 38–45.
7. Boreskov A.V., Kharlamov A.A. Osnovy raboty s tekhnologiej CUDA. M.: DMK Press, 2010. 232 s.
8. Volkova E.V., Uspenskij A.B. Otsenki parametrov oblachnogo pokrova po dannym geostatsionarnogo MISZ METEOSAT-9 kruglosutochno v avtomaticheskom rezhime // Sovr. probl. dist. zondir. Zemli iz kosmosa. 2010. T. 7. № 3. S. 65–73.
9. Dejvis Sh.M., Landgrebe D.A., Fillips T.L., Svejn F.Kh., Khoffer R.M., Landenlaub D.S., Sieva Le R.F. / Pod red. F.Kh. Svejna, Sh.M. Dejvis. M.: Nedra, 1983. 396 s.
10. Zagorujko N.G. Kognitivnyj analiz dannykh. Novosibirsk: Akad. Izd-vo GEO, 2013. 186 s.
11. Kobzar' A.I. Prikladnaya matematicheskaya statistika: dlya inzhenerov i nauchnykh rabotnikov. M.: Fizmatlit, 2006. 816 s.
12. Kolodnikova N.V. Obzor teksturnykh priznakov dlya zadach raspoznavaniya obrazov // Dokl. Tomskogo gos. un-ta sistem upravleniya i radioehlektroniki. 2004. T. 9. № 1. S. 113–124.
13. Kruglov V.V., Dli M.I., Golunov R.Yu. Nechetkaya logika i iskusstvennye nejronnye seti. M.: Fizmatlit, 2001. 224 s.
14. Osovskij S. Nejronnye seti dlya obrabotki informatsii / Per. s pol'sk. I.D. Rudinskogo. M.: Finansy i statistika, 2002. 344 s.
15. Skorokhodov A.V., Aksenov S.V., Aksenov A.V., Lajkom D.N. Ispol'zovanie razlichnykh vychislitel'nykh sistem dlya resheniya zadachi avtomaticheskoj klassifikatsii oblachnosti po sputnikovym dannym MODIS na osnove veroyatnostnoj nejronnoj seti // Izv. Tomskogo politekhn. un-ta. 2016. T. 327. № 1. S. 30–39.
16. Federal'naya sluzhba po gidrometeorologii i monitoringu okruzhayuschej sredy (Rosgidromet). Kod dlya operativnoj peredachi dannykh prizemnykh meteorologicheskikh nablyudenij s seti stantsij Rosgidrometa. M.: «Triada. ltd», 2013. 79 s.
17. Shakina N.P. Lektsii po dinamicheskoj meteorologii. M.: «Triada. ltd», 2013. 160 s.
18. Astafurov V.G., Kuriyanovich K.V., Skorokhodov A.V. Methods for automatic cloud classifi cation from MODIS data // Izv. Atm. and Oc. Phys. 2016. V. 52. P. 1110–1119.
19. Astafurov V.G., Kuriyanovich K.V., Skorokhodov A.V. A statistical model for describing the texture of cloud cover images from satellite data // Russian Meteorol. and Hydrol. 2017. V. 42. № 4. P. 248–257.
20. Bankert R.L., Mitrescu C., Miller S.W., Wade R.H. Comparison of GOES cloud classification algorithms employing explicit and implicit physics // J. Appl. Meteor. Clim. 2009. V. 48. P. 1411–1421.
21. Baum B.A., Tovinkere V., Titlow J., Welch R.M. Automated cloud classifi cation of global AVHRR data using a fuzzy logic approach // J. Appl. Meteor. 1997. V. 36. P. 1519–1540.
22. Jin W., Gong F., Zeng X., Fu R. Classifi cation of clouds in satellite imagery using adaptive fuzzy sparse representation // Sensors. 2016. V. 16. doi:10.3390/s16122153.
23. Haralick R.M., Shanmugam K, Dinstein I. Textural features for image classifi cation // IEEE Transact. Syst., Man and Cybern. 1973. V. SMC–3. № 6. P. 610–621.
24. Liu Y, Xia J, Shi C.-X., Hong Y. An improved cloud classifi cation algorithm for China’s FY-2C multi-channel images using artifi cial neural network // Sensors. 2009. V. 9. P. 5558–5579.
25. Menzel W.P., Frey R.A., Baum B.A. Cloud top properties and cloud phase. Algorithm theoretical basis document. Collection 006 update. Greenbelt, Maryland, USA: Goddard Space Flight Center, 2013. 70 p.
26. MODIS [electronic resource] / Moderate Resolution Imaging Spectroradiometer, 2000–2017. URL: https://modis.gsfc.nasa.gov/about/specifi  cations.php (access data 30.08.2017). Specht D.F. Probabilistic neural networks // Neural Netw. 1990. V. 3. P. 109–118.
27. Suzue H., Imai T., Mouri K. High-resolution cloud analysis information derived from Himawari-8 data // Meteorol. Sat. Center Techn. Note. 2016. № 61. P. 43–51.
28. Tapakis R., Charalambides A.G. Equipment and methodologies for cloud detection and classifi cation: A review // Solar Energy. 2013. V. 95. P. 392–430.
29. Unser M. Sum and diff erence histograms for texture classifi - cation // IEEE Transact. Syst., Pattern Anal. and Machine Intell. 1986. V. PAMI–8. № 1. P. 118–125.
30. Weszka J.S., Dyer C.R., Rosenfeld A. A comparative study of texture measures for terrain classifi cation // IEEE Transact. Syst., Man and Cybernet. 1976. V. SMC–6. № 4. P. 269–285.

Система Orphus

Loading...
Up