Advertisement

Izvestiya, Atmospheric and Oceanic Physics

, Volume 53, Issue 9, pp 1112–1122 | Cite as

Satellite Image Classification Method Using the Dempster–Shafer Approach

Methods and Means of Processing and Interpretation of Space Information
  • 10 Downloads

Abstract

In this paper the problem of the supervised classification of satellite images is considered. A new image classification method focused on application under conditions when the training sample is (in particular, considerably) contaminated is proposed. The method is based on using the Dempster–Shafer evidence theory and is applicable both for hyperspectral and multispectral satellite images. Problems of organizing the supervised classification process and content of its constitutive procedures are presented. The developed method has been implemented algorithmically and in software. Results obtained in the classification of hyperspectral images by the proposed method testify to its efficiency.

Keywords

satellite image supervised classification Dempster–Shafer evidence theory contaminated training sample 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Beynon, M.J., Curry, B., and Morgan, P., The Dempster–Shafer theory of evidence: An alternative approach to multicriteria decision modeling, Omega: Int. J. Manage. Sci., 2000, vol. 28, no. 1, pp. 37–50.CrossRefGoogle Scholar
  2. Bondur, V.G. and Starchenkov, S.A., Methods and programs for processing and classification of aerospace images, Izv. Vyssh. Uchebn. Zaved., Geod. Aerofotos’emka, 2001, no. 3, pp. 118–143.Google Scholar
  3. Bondur, V.G. and Vorob’ev, V.E., Methods for processing aerospace images obtained from monitoring of oil and gas industry objects, in Aerokosmicheskii monitoring ob”ektov neftegazovogo kompleksa (Aerospace Monitoring of Oil and Gas Industry Objects), Bondur, V.G., Ed., Moscow: Nauchnyi mir, 2012, pp. 395–409.Google Scholar
  4. Bondur, V.G., Modern approaches to processing hyperspectral aerospace images, in Giperspektral’nye pribory i tekhnologii (Hyperspectral Instrumentation and Technologies), Krasnogorsk, 2013, pp. 14–18.Google Scholar
  5. Bondur, V.G., Modern approaches to processing large hyperspectral and multispectral aerospace data flows, Izv., Atmos. Ocean. Phys., 2014, vol. 50, no. 9, 840–852.CrossRefGoogle Scholar
  6. Burges, C.J.C., A tutorial on support vector machines for pattern recognition, Data Mining Knowledge Discovery, 1998, vol. 2, no. 2, pp. 121–167.CrossRefGoogle Scholar
  7. Chang, Ch.I., Hyperspectral Data Exploitation: Theory and Applications, New York: John Willey & Sons, 2007.CrossRefGoogle Scholar
  8. Cochran, W.G., Sampling Techniques, New York: John Wiley & Sons, 1977.Google Scholar
  9. Congalton, G. and Green, K., Assessing the Accuracy of Remotely Sensed Data: Principles and Practices, Boca Raton, FL: CRC, 2009.Google Scholar
  10. Dempster, A., Upper and lower probabilities induced by a multivalued mapping, Ann. Math. Stat., 1967, no. 38, pp. 325–339.CrossRefGoogle Scholar
  11. ENVI Ver. 4.7, Visual Information Solutions, December 2009.Google Scholar
  12. Kel’bert M.Ya. and Merlushkin, A.I., On parameter estimation from distorted data, in Nauchno-tekhnicheskaya informatsiya. Ser. 2: Informatsionnye protsessy i sistemy (Scientific and Technical Information. Ser. 2: Information Processes and Systems), Moscow: VINITI RAN, 1994, pp. 20–25.Google Scholar
  13. Kozoderov, V.V., Kondranin, T.V., Kazantsev, O.Yu., Bobylev, V.I., Shcherbakov, M.V., Borzyak, V.V., Dmitriev, E.V., Egorov, V.D., Kamentsev, V.P., Belyakov, A.Yu., and Loginov, S.B., Processing and interpretation of hyperspectral aerospace measurement data for remote diagnostics of natural and technogenic objects, Issled. Zemli Kosmosa, 2009, no. 2, pp. 36–54.Google Scholar
  14. Lyal’ko, V.I., Popov, M.O., and Fedorovskii, O.D., Bagatospektral’ni metodi DZZ v zadachakh prirodokoristuvannya (Multispectral Methods of Remote Sensing of the Earth in Problems of Nature Management), Kiev: Naukova dumka, 2006.Google Scholar
  15. Marcin, J., Effects of Contaminants on Spectral Signatures: Senior Thesis, Rochester Inst. Technol., Chester F. Carlson Center for Im. Sci., 2003.Google Scholar
  16. Momani, B.A., McClean, S., and Morrow, P., Using Dempster–Shafer to incorporate knowledge into satellite image classification, Artif. Intel. Rev., 2006, vol. 25, pp. 161–178. doi 10.1007/s10462-007-9027-4CrossRefGoogle Scholar
  17. Popov, M.A., Methodology for estimating the accuracy of object classification on space images, Probl. Upr. Inf., 2007, no. 1, pp. 97–103.Google Scholar
  18. Romanov, A.A. and Rubanov, K.A., Efficiency of nonparametric classifiers with a limited training sample, Zh. Sib. Fed. Univ.: Tekh. Tekhnol., 2012, no. 5, pp. 495–506.Google Scholar
  19. Ruwet, C. and Haesbroeck, G., Impact of contamination on training and test error rates in statistical clustering, in Commun. Stat., Simul. Comput., 2011, vol. 40, no. 3, pp. 394–411.CrossRefGoogle Scholar
  20. Shafer, G., A Mathematical Theory of Evidence, Princeton: Princeton University Press, 1976.Google Scholar
  21. Smets, P., Henrion, M., Shachter, R.D., Kanal, L.N., and Lemmer, J.F., Constructing the pignistic probability function in a context of uncertainty, in Uncertainty in Artificial Intelligence, Amsterdam: North Holland, 1990, vol. 5, pp. 29–40.CrossRefGoogle Scholar
  22. Taroun, A. and Yang, J.B., Dempster–Shafer theory of evidence: Potential usage for decision making and risk analysis in construction project management, Built Human Environ. Rev., 2011, vol. 4, special no. 1, pp. 155–166.Google Scholar
  23. Tso, B., Classification Methods for Remotely Sensed Data. London: Tailor and Francis, 2001.CrossRefGoogle Scholar
  24. Utkin L.V. Analiz riska i prinyatie reshenii pri nepolnoi informatsii (Risk Analysis and Decision Making with Incomplete Information), St. Petersburg: Nauka, 2007.Google Scholar
  25. Venttsel’, E.S., Teoriya veroyatnostei (Probability Theory), Moscow: Vysshaya shkola, 1999.Google Scholar
  26. Yan, D., Gong, P., Chen, A., and Zhong, L., Classification under data contamination with application to remote sensing image misregistration, J. Comp. Res. Reposit. CoRR, 2011, abs/1101.3.Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2017

Authors and Affiliations

  1. 1.Scientific Centre for Aerospace Research of the EarthNational Academy of Sciences of UkraineKyivUkraine

Personalised recommendations