Algorithms of object identification on the basis of hyperspectral Earth survey data using fuzzy linear regression


An approach to solving problems of identifying Earth surface objects on the basis of hyperspectral survey data obtained from space complexes based on the comparison of hyperspectral characteristics of the objects investigated with a set of reference signatures is presented in the paper. Algorithms of object identification with the use of the theory of fuzzy sets are proposed: an identification algorithm based on fuzzy linear regression and an algorithm of consolidation of results of different identification solutions. The fuzzy linear regression algorithm is based on the use of non-symmetrical triangular fuzzy numbers. This approach, used earlier in solving approximation tasks and assessing the unique character of electronic map fragments is now used for the first time for the identification of hyperspectral characteristics. The choice is founded on the fact that fuzzy linear regression makes identification possible in ambiguous conditions. The results of experimental studies of the proposed algorithms based on real hyperpsectral survey data (from spacecraft «Resurs-P» N1) are presented in the form of 10 images. Identification reliability is shown to increase by 6.1 % as compared with one of the initial algorithms yielding the best solution in the case of consolidating results obtained by using algorithms based on the Euclidean distance similarity measure, the angle similarity measure, as well as fuzzy similarity measures. 

About the authors

S. V. Trukhanov

Branch of the joint stock company Space Rocket Center «Progress» – Specialist Design Office «Spectrum», Ryazan

Author for correspondence.

Russian Federation

Deputy Head of department


  1. Antonushkina S.V., Eremeev V.V., Makarenkov A.A., Moskvitin A.E., Yudakov A.A. Novye vozmozhnosti analiza ob"ektov zemnoy poverkhnosti na osnove giperspektral'noy s"emki. Sbornik trudov II Vserossiyskoy nauchno-tekhnicheskoy konferentsii «Aktual'nye problemy raketno-kosmicheskoy tekhniki» (Kozlovskie chteniya). Samara: Samarskiy nauchnyy tsentr RAN Publ., 2011. P. 26-27. (In Russ.)
  2. Akhmetov R.N., Stratilatov N.R., Yudakov A.A., Vezenov V.I., Eremeev V.V. Osnovnye napravleniya issledovaniy po sozdaniyu tekhnologiy obrabotki dannykh giperspektral'noy s"emki Zemli. Sb. tezisov dokladov nauchno-tekhnicheskoy konferentsii «Giperspektral'nye pribory i tekhnologii». Krasnogorsk: OAO «Krasnogorskiy zavod im. S.A. Zvereva» Publ., 2013. P. 23-24. (In Russ.)
  3. Akhmetov R.N., Stratilatov N.R., Yudakov A.A., Vezenov V.I., Eremeev V.V. Models of formation and some algorithms of hyperspectral image processing. Izvestiya – Atmospheric and Ocean Physics. 2014. V. 50, Iss. 9. P. 867-877. doi: 10.7868/S0205961414010011
  4. Yudakov A.A. Novye napravleniya rabot po analizu kosmicheskikh giperspektral'nykh snimkov poverkhnosti Zemli. Tezisy dokladov XVI Vserossiyskoy nauchno-tekhnicheskoy konferentsii «Novye informatsionnye tekhnologii v nauchnykh issledovaniyakh». Ryazan: RyazanState Radio Engineering University Publ., 2011. P. 237-238. (In Russ.)
  5. Demidova L.A., Myatov G.N. Uniqueness estimation technique of the electronic map''s fragments based on the fuzzy logic. Vestnik of Samara State Technical University. Technical Sciences Series. 2013. No. 4 (40). P. 14-26. (In Russ.)
  6. Myatov G.N. Formirovanie unikal'nykh fragmentov elektronnoy karty s ispol'zovaniem nechetkoy lineynoy regressii. Mezhvuzovskiy sbornik nauchnykh trudov «Matematicheskoe i programmnoe obespechenie vychislitel'nykh sistem». Ryazan: Ryazan State Radio Engineering University Publ., 2012. P. 169-181. (In Russ.)
  7. Haekwan L., Tanaka H. Fuzzy approximations with non-symmetric fuzzy parameters in fuzzy regression analysis. Journal of the Operations Research Society of Japan. 1999. V. 42, Iss. 1. P. 98-112.
  8. Haekwan L., Tanaka H. Fuzzy regression analysis by quadratic programming reflecting central tendency. Behaviormetrika. 1998. V. 25, Iss. 1. P. 65-80. doi: 10.2333/bhmk.25.65
  9. Sakawa M., Yano H. Multiobjective fuzzy linear regression analysis for fuzzy input-output data. Fuzzy Sets and Systems. 1992. V. 47, Iss. 2. P. 173-181. doi: 10.1016/0165-0114(92)90175-4
  10. Trukhanov S.V. Using fuzzy linear regression in hyperspectral removal data classification algorithms. Proceeding of the XX-th International Open Science Conference «Modern informatization problems in economics and safety». 2015. P. 56-61.
  11. Demidova L.A., Tishkin R.V., Trukhanov S.V. The Objects Hyperspectral Feature Identification Algorithms in the Earth Remote Sensing Tasks. Digital signal processing. 2014. No. 3. P. 30-37. (In Russ.)
  12. Demidova L.A., Tishkin R.V., Trukhanov S.V. Problem solution of objects hyperspectral feature identification by means of intellectual data processing system of hyperspectral removal. Vestnik of Ryazan State Radioengineering University. 2014. No. 1 (47). P. 10-18. (In Russ.)
  13. Trukhanov S.V. Primenenie nechetkoy lineynoy regressii pri identifikatsii giperspektral'nykh kharakteristik ob"ektov. Sbornik trudov Vserossiyskoy nauchno-tekhnicheskoy konferentsii «Teoreticheskie i prikladnye problemy razvitiya i sovershenstvovaniya avtomatizirovannykh sistem upravleniya voennogo naznacheniya». Saint Petersburg: Voenno-kosmicheskaya akademiya imeni A.F. Mozhayskogо Publ., 2014. P. 401-406. (In Russ.)
  14. Zadeh L.A. The concept of a linguistic variable and its application to approximate reasonin. American Elsevier Publishing Company, 1973. 165 p.
  15. Van Der Weken D., Nachtegael M., Kerre E.E. An overview of similarity measures for images. IEEE International Conference on Acoustics Speech and Signal Processing. 2002. P. 3317-3320. doi: 10.1109/icassp.2002.1004621



Abstract - 76

PDF (Russian) - 38

Article Metrics

Metrics Loading ...




  • There are currently no refbacks.

Copyright (c) 2016 VESTNIK of the Samara State Aerospace University

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies