Vol. 27, issue 07, article # 13

Astafurov V.G., Evsyutkin T.V., Kuriyanovich K.V., Skorokhodov A.V. Statistical model of cirrus cloud textural features based on MODIS satellite images. // Optika Atmosfery i Okeana. 2014. V. 27. No. 07. P. 640-646 [in Russian].
Copy the reference to clipboard
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.

Keywords:

cirrus clouds, textural features, statistical model, classification, satellite data

References:

1. Bankert R.L., Mitrescu C., Miller S.W., Wade R.H. Comparison of GOES cloud classification algorithms employing explicit and implicit physics // J. Appl. Meteorol. Climatol. 2009. V. 48. P. 1411–1421.
2. Lafont D., Jourdan O., Guillement B. Mesoscale cloud pattern classification over ocean with a neural network using a new index of cloud variability // Int. J. Remote Sens. 2006. V. 27. P. 3533–3552.
3. Astafurov V.G., Skorohodov A.V. Nejrosetevoj klassifikator oblachnosti po sputnikovym dannym // Inform. tehnol. 2012. N 7. P. 32–37.
4. Volkova E.V., Uspenskij A.B. Ocenki parametrov oblachnogo pokrova po dannym geostacionarnogo MISZ METEOSAT-9 kruglosutochno v avtomaticheskom rezhime // Sovremennye problemy distancionnogo zondirovanija Zemli iz kosmosa. 2010. V. 7, N 3. P. 65–73.
5. Kod dlja operativnoj peredachi dannyh prizemnyh gidrometeorologicheskih nabljudenij s seti stancij Goskomgidrometa SSSR, raspolozhennyh na sushe (vkljuchaja beregovye stancii) KN-01, nacional'nyj variant mezhdunarodnogo koda FM-12-IX SYNOP. L.: Gidrometeoizdat, 1989. 64 p.
6. Baran A. A review of the light scattering properties of cirrus // J. Quant. Spectrosc. Radiat. Transfer. 2009. V. 110. P. 1239–1260.
7. Solomatov D.V., Afonin S.V., Belov V.V. Postroenie oblachnoj maski i udalenie poluprozrachnoj oblachnosti na sputnikovyh snimkah ETM+/Landsat-7 // Optika atmosf. i okeana. 2013. V. 26, N 12. P. 798–803.
8. Gonsales R., Vuds R. Cifrovaja obrabotka izobrazhenij. M.: Tehnosfera, 2005. 1072 p.
9. Weszka J.S., Dyer C.R., Rosenfeld A. A comparative study of texture measures for terrain classification // IEEE Transaction on Systems, Man and Cybernetics. April 1976. V. SMC-6, N 4. P. 269–285.
10. Haralick R.M., Shanmugam K., Dinstein I. Textural features for image classification // IEEE Transactions on Systems, Man and Cybernetics. November 1973. V. SMC-3, N 6. P. 610–621.
11. Unser M. Sum and difference histograms for texture classification // IEEE Transaction on Systems, Pattern Analysis and Machine Intelligence. January 1986. V. PAMI-8, N 1. P. 118–125.
12. Zagorujko N.G. Prikladnye metody analiza dannyh i znanij. Novosibirsk: IM SO RAN, 1999. 270 p.
13. Osovskij S. Nejronnye seti dlja obrabotki informacii / Per. s pol'sk. I.D. Rudinskogo. M.: Finansy i statistika, 2002. 344 p.
14. Astafurov V.G., Skorohodov A.V. Segmentacija sputnikovyh snimkov oblachnosti po teksturnym priznakam na osnove nejrosetevyh tehnologij // Issled. Zemli iz kosmosa. 2011. N 6. P. 10–20.
15. Kobzar' A.I. Prikladnaja matematicheskaja statistika. Dlja inzhenerov i nauchnyh rabotnikov. M.: Fizmatlit, 2006. 816 p.
16. MathWave [Electronic resource]: EasyFit – Easily Fit Distributions to Your Data! Electronic data. – Dnepropetrovsk, 2004–2014. – URL: http://www.mathwave.com/help/easyfit/index.html (Accessеd 12.02.2014).

Back