On Automated Recognition of Cloud Types Instructions

Nina Aprausheva, Irina Gorlach, Aleksandr Zhelnin, Stanislav Sorokin

Abstract

Results of the recognition of multi-spectral satellite data by an automated classification procedure (ACP) are presented. The procedure is based on the approximation of an unknown probability density of a given set of observations by a multi-dimensional Gaussian mixture. For a given number of mixture components, optimal estimates for unknown parameters are found by the Day-Shlezinger algorithm as such solution of simultaneous likelihood equations, that maximizes the likelihood function. Optimal number of classes is determined by the step-by-step testing of two composite statistical hypotheses. The classification of a set of observations is performed by the Bayes rule. To reduce the calculus number, a preliminary analysis of the structure of the investigated set is carried out, which provides rough estimates of the number of classes and their basic characteristics. Results of automatic classification of the main types of clouds and underlying surface are described.

References

  1. Solov'eva, I. S., Sonechkin, D. M., and Kharitonov, V. F.: Computerized Processing and Analysis of Television Images of Clouds. In Tr. Gidrometeorol. Nauchno-Issled. Tsentra (1971) no. 73, 64-74
  2. Bakst, L. A. and Fedorova, N. N.: A Study of Clouds for Synoptic Analysis Based on Multispectral AVHRR Data from a NOAA Satellite. In Issl. Zemli iz Kosmosa (1994) no. 4, 3- 8
  3. Tokuno, M. and Tsuchija, K.: Classification of Cloud Types Based on Data of Multiple Satellite Sensors. In Adv. Space Res. (1994) Vol. 14, no. 3, 199-206
  4. Peak, J. E. and Tag, P. M.: Segmentation of Satellite Imagery Using Hierarchical Thresholding and Neural Networks. In J. Appl. Meteorol. (1994) Vol. 33, no. 5, 605-616
  5. Strabala, K. I., Ackerman, S. A., and Menzel, W.P.: Cloud Properties Inferred from 8-12 µm Data. In J. Appl. Meteorol. (1994) Vol. 33, no. 2, 212-219
  6. Bakst, L. and Fedorova, N.: On Some Methods of Synoptic Analysis Based on the Study of the Multispectral Satellite Data Variation. In Proc. 9th Meteorological Satellite Data Users' Conj.. Locarno, Switzerland, Darmstadt: EUMETSAT (1992) 25-32
  7. Bankertt, R. L.: Cloud Classification of AVHRR Imagery in Maritime Regions Using a Probabilistic Neural Network. In J. Appl. Meteorol. (1994) Vol. 33, no. 8, 1023-1039
  8. Voloshin, G.Ya., Burlakov, I.A., and Kosenkova, S.T.: Statisticheskie metody resheniya zadach raspoznavaniya, osnovannye na approksimatsionnom podkhode (Statistical Methods for Recognition Problems Based on the Approximation Approach). Vladivostok, ch. 1 (1992)
  9. Careira-Perpiñán, M. A., Williams, C.: On the number of modes of a Gaussian mixture. Inform. In Res. Report EDI-INF-RR-0159. School of Inf. Univ. of Edinburg (2003)
  10. Anderson, T. W.: An Introduction to Multivariate Statistical Analysis. Wiley, New York (1958). Translated under the title Vvedenie v mnogomernyi statisticheskii analiz. Fizmatgiz, Moscow (1963)
  11. Day, N. E.: Estimating the Components of a Mixture of Normal Distributions. In Biometrika (1969) Vol. 56, no. 3, 463-474.
  12. Aprausheva, N. N.: Analysis of a Splitting Algorithm for the Mixture of Normally Distributed Classes, In Aivazyan. S.A. (ed.): Mnogomernyi statisticheskii analiz v sotsial'noekonomicheskikh issledovaniyakh (Multidimensional Analysis in Social and Economic Studies), Nauka, Moscow (1974) 135-150
  13. Aprausheva, N. N.: Transformation of Features in the Statistical Solution of an Automated Classification Problem. In Izv. Akad. Nauk SSSR, Ser: Tekhn. Kibern. (1985) no. 2, 167- 174
  14. Aprausheva, N. N.: Novyi podkhod k obnaruzheniyu klasterov (A New Approach in Cluster Detection). Vychisl. Tsentr Ross. Akad. Nauk, Moscow (1993)
  15. Duran, B. S. and Odell, P. L.: Cluster Analysis. A Survey, Springer., Berlin (1974). Translated under the title Klasternyi analiz, Statistika, Moscow (1975)
  16. Aprausheva, N. N.:(1981) Determination of the Number of Classes in Classification Problems. In Izv. Akad. Nauk SSSR. Ser: Tekhn. Kibern. (1981) no. 3, 71-77, no. 5, 153-160.
  17. Aprausheva, N. N., Bakst, L. A., Gorlach, I. A., et al.: On the Recognition of Types of Frontal Clouds Based on Satellite Data. Vychisl. Tsentr Ross. Akad. Nauk, Moscow (1996)
  18. Cramér, H.: Mathematical Methods of Statistics. Princeton Univ. Press, Princeton New Jersey (1946). Translated under the title Matematicheskie metody statistiki. Mir, Moscow (1976)
  19. Wilkes, S. S.: Mathematical Statistics. Wiley, New York: (1962). Translated under the title Matematicheskaya statistika. Nauka, Moscow (1973)
Download


Paper Citation


in Harvard Style

Aprausheva N., Gorlach I., Zhelnin A. and Sorokin S. (2013). On Automated Recognition of Cloud Types Instructions . In Proceedings of the 4th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-4, (VISIGRAPP 2013) ISBN 978-989-8565-50-1, pages 114-120. DOI: 10.5220/0004395001140120


in Bibtex Style

@conference{imta-413,
author={Nina Aprausheva and Irina Gorlach and Aleksandr Zhelnin and Stanislav Sorokin},
title={On Automated Recognition of Cloud Types Instructions},
booktitle={Proceedings of the 4th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-4, (VISIGRAPP 2013)},
year={2013},
pages={114-120},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004395001140120},
isbn={978-989-8565-50-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Workshop on Image Mining. Theory and Applications - Volume 1: IMTA-4, (VISIGRAPP 2013)
TI - On Automated Recognition of Cloud Types Instructions
SN - 978-989-8565-50-1
AU - Aprausheva N.
AU - Gorlach I.
AU - Zhelnin A.
AU - Sorokin S.
PY - 2013
SP - 114
EP - 120
DO - 10.5220/0004395001140120