Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 21, 2024
Number 1
Volume 20, 2023
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 19, 2022
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 18, 2021
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 17, 2020
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 16, 2019
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 15, 2018
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 14, 2017
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 13, 2016
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 12, 2015
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 11, 2014
Number 1 Number 2 Number 3 Number 4
Volume 10, 2013
Number 1 Number 2 Number 3 Number 4
Volume 9, 2012
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 8, 2011
Number 1 Number 2 Number 3 Number 4
Volume 7, 2010
Number 1 Number 2 Number 3 Number 4
Issue 6, 2009
Volume 1 Volume 2
Issue 5, 2008
Volume 1 Volume 2
Issue 4, 2007
Volume 1 Volume 2
Issue 3, 2006
Volume 1 Volume 2
Issue 2, 2005
Volume 1 Volume 2
Issue 1, 2004
Volume 1
Search
Find:
русский
ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2017, Vol. 14, No. 5, pp. 9-18

Classification of the main cloud type textures from MODIS data using fuzzy systems

V.G. Astafurov 1, 2 , T.V. Evsyutkin 1 , K.V. Kuryanovich 1, 2 , A.V. Skorokhodov 1 
1 V.E. Zuev Institute of Atmospheric Optics SB RAS, Tomsk, Russia
2 Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russia
Accepted: 07.07.2017
DOI: 10.21046/2070-7401-2017-14-5-9-18
The paper presents an algorithm of cloud classification on MODIS satellite images with 250-meter spatial resolution based on fuzzy logic methods and neural network technologies, which makes it possible to allocate image areas with a similar texture in relation to several cloud types with a close membership degree, and corresponds to the real dynamics of cloud formations. To describe cloud images texture, the methods are used based on gray level co-occurrence matrices (GLCM), vectors of difference (GLDV), sum and difference histograms (SADH) and statistical features of intensity for individual pixels on images (ODSH). Reference image sets for different cloud types have been formed by comparing the archival data of terrestrial weather stations with MODIS satellite images. The technique is discussed for building a set of effective texture features of cloud images based on comparative analysis of sampling histogram deviations. To characterize fluctuations of texture feature values for different cloud type images, a statistical model was developed that includes 17 two-parameter probability density functions with estimation of the features’ parameters. A method was proposed of neural network membership functions initialization using statistical model of image textures. In the course of numerical experiments an assessment was obtained of probability of correct image classification for ten basic cloud types which reached 0.81.
Keywords: cloud types, MODIS, image classification, texture features, texture statistical model, membership functions, fuzzy system
Full text

References:

  1. Astafurov V.G., Skorokhodov A.V., Segmentatsiya sputnikovykh snimkov oblachnosti po teksturnym priznakam na osnove neirosetevykh tekhnologii (Segmentation of satellite cloud images based on texture features and neural network technologies), Issledovanie Zemli iz kosmosa, 2011, No. 6, pp. 10–20.
  2. Astafurov V.G., Evsyutkin T.V., Kur’yanovich K.V., Skorokhodov A.V., Statisticheskaya model’ tekstury izobrazhenii razlichnykh tipov oblachnosti po dannym MODIS (Statistical model of the texture images of different types of clouds on MODIS data), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2013, Vol. 10, No. 4, pp. 188–197.
  3. Astafurov V.G., Skorokhodov A.V., Primenenie neirosetevykh tekhnologii dlya klassifikatsii oblachnosti po teksture snimkov MODIS vysokogo razresheniya (Application of neural network technologies for classification of clouds according to the texture of high resolution MODIS images), Issledovanie Zemli iz kosmosa, 2014, No. 5, pp. 39–49.
  4. Astafurov V.G., Aksenov S.V., Evsyutkin T.V., Klassifikatsiya peristoi oblachnosti po dannym MODIS s pomoshch’yu nechetkoi neironnoi seti (Classification of cirrus clouds on MODIS data using a fuzzy neural network), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2014, Vol. 11, No. 4, pp. 265–275.
  5. Astafurov V.G., Kur’yanovich K.V., Skorokhodov A.V., Metody avtomaticheskoi klassifikatsii oblachnosti po sputnikovym snimkam MODIS (Methods of automatic classification of clouds on MODIS), Issledovanie Zemli iz kosmosa, 2016, No. 4, pp. 35–45.
  6. 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 (Cloud Atlas), Saint Petersburg: D’ART, 2011, 248 p.
  7. Volkova E.V., Otsenki parametrov oblachnogo pokrova, osadkov i opasnykh yavlenii pogody po dannym radiometra AVHRR c MISZ serii NOAA kruglosutochno v avtomaticheskom rezhime (Estimates of the parameters of the cloud cover, precipitation and dangerous weather phenomena according to the AVHRR radiometer with MISZ of the NOAA series around the clock in automatic mode), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2013, Vol. 10, No. 3, pp. 66–74.
  8. Vyatchenin D.A., Nechetkie metody avtomaticheskoi klassifikatsii (Fuzzy methods of automatic classification), Minsk: UP “Tekhnoprint”, 2004, 219 p.
  9. Kobzar’ A.I., Prikladnaya matematicheskaya statistika (Applied mathematical statistics), Moscow: Fizmatlit, 2006, 816 p.
  10. Kod dlya operativnoi peredachi dannykh prizemnykh meteorologicheskikh nablyudenii s seti stantsii Rosgidrometa (The code for the operational data transfer of surface meteorological observations from the Roshydromet network (SYNOP)), Moscow, Triada. Ltd, 2013, 79 p.
  11. Kruglov V.V., Dli M.I., Golunov R.Yu., Nechetkaya logika i iskusstvennye neironnye seti (Fuzzy logic and artificial neural networks), Moscow: Fizmatlit, 2000, 224 p.
  12. Oblaka i oblachnaya atmosfera (Clouds and a cloudy atmosphere), Leningrad: Gidrometeoizdat, 1989, 647 p.
  13. Bankert R.L., Mitrescu C., Miller S.W., Wade R.H., Comparison of GOES cloud classification algorithms employing explicit and implicit physics, Journal of Applied Meteorology and Climatology, 2009, Vol. 48, pp. 1411–1421.
  14. Baum B.A., Tovinkere V., Titlow J., Welch R.M., Automated cloud classification of global AVHRR data using a fuzzy logic approach, Journal of Applied Meteorology, 1997, Vol. 36, pp. 1519–1540.
  15. Haralick R.M., Shanmugam K., Dinstein I., Textural features for image classification, IEEE Transactions on Systems, Man and Cybernetics, November 1973, Vol. SMC-3, No. 6, pp. 610–621.
  16. http://www.mathwave.com/help/easyfit/index.html.
  17. Smith S.F., A learning system based on genetic adaptive algorithms: Doctoral Dissertation, University of Pittsburgh, PA, 1980.
  18. Tag P.M., Bankert R.L., Brody L.R., An AVHRR multiple cloud-type classification package, J. Appl. Meteor., 2000, Vol. 39, pp. 125–134.
  19. 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, Vol. SMC-6, No. 4, pp. 269–285.
  20. Unser M., Sum and difference histograms for texture classification, IEEE Transaction on Systems, Pattern Analysis and Machine Intelligence, January 1986, Vol. PAMI-8, No. 1, pp. 118–125.