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. 7, pp. 9-19

Hyperspectral image classification using cluster data structure

E.V. Ramenskaya 1 , M.P. Kuznetsov 2 , V.V. Ermakov 1 , O.R. Barkova 1 , A.A. Bran 1 
1 Samara State Technical University, Samara, Russia
2 Moscow Institute of Physics and Technology, Dolgoprudny, Moscow Region, Russia
Accepted: 20.11.2017
DOI: 10.21046/2070-7401-2017-14-7-9-19
The problem of two-class classification of a hyperspectral image is solved, with the subdivision into clusters within each class. The images were obtained during flight tests of a laboratory aircraft. At the first stage, the algorithm performs clustering of the areas of interest. The likelihood function for a mixture of Gaussian distributions is maximized. At the second stage, the algorithm uses the Mahalanobis distances to cluster centers as a feature space. In this space, the classification is carried out by the decision tree method which minimizes the classification errors. The algorithm has low computational complexity: the learning stage is linearly dependent on the number of marked pixels. The proposed method is interpreted within the framework of the expert field. The learning phase of the algorithm has linear computational complexity by the number of objects. The proposed method of classification makes it possible to identify with high accuracy the areas of interest in the hyperspectral image. The algorithm allowed to separate areas of oil contaminated soil from other poorly reflecting objects. The result of the algorithm is the image in which only areas with the presence of petroleum products are indicated by color, and all other areas are darkened. This image has the same resolution as the original image. Georeference is preserved. It is possible to count the marked pixels of the image in the received image to calculate the area of the contaminated sites.
Keywords: hyperspectral image, cluster hypothesis, mixture of distributions, Mahalanobis distance, decision tree
Full text

References:

  1. Gur’yanova A.O., Ermakov V.V., Ramenskaya E.V., Mandra A.G., Poluchenie opornykh spektral’nykh signatur pri giperspektral’noi s"emke (Obtaining of Support Spectral Signals during Hyperspectral Survey), Ekologiya i promyshlennost’ Rossii, 2014, No. 10, pp. 44–47.
  2. Orlov D.S., Almosova Ya.M., Bocharinova E.A., Lopukhina O.V., Ispol’zovanie metoda otrazhatel’noi sposobnosti neftezagryaznennykh pochv pri distantsionnom monitoringe (The use of oil-contaminated soil reflectance for remote monitoring), Aerokosmicheskie metody v pochvovedenii, 1989, No. 1, pp. 73–75.
  3. Tokareva O.S., Obrabotka i interpretatsiya dannykh distantsionnogo zondirovaniya Zemli: uchebnoe posobie (Processing and interpretation of remote sensing data), Izd-vo Tomskogo politekhnicheskogo universiteta, 2010, 148 p.
  4. Uvarov I.A., Loupian E.A., Matveev A.M., Mazurov A.A., Lavrova O.Yu., Mityagina M.I., Organizatsiya raboty s dannymi sputnikovykh giperspektral’nykh nablyudenii dlya issledovaniya protsessov v Mirovom okeane (Management of hyperspectral remote sensing data for studies of world ocean processes), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2014, Vol. 11, No. 1, pp. 200–212.
  5. Chertes K.L., Zelentsov D.V., Bal’zannikov M.I., Grishin B.M., Andreev S.Yu., Intensivnaya biotermicheskaya obrabotka osadkov neftesoderzhashchikh stochnykh vod (Intensive biothermal treatment of precipitation oily wastewater), Elektronnyi nauchnyi zhurnal Neftegazovoe delo, 2012, No. 4, pp. 261–266.
  6. Ball G.H., Hall D.J., Isodata, a method of data analysis and pattern classification, Stanford Research Institute Publisher, 1965, 76 p.
  7. Broomhead D.S., Lowe D., Radial basis functions, multi-variable functional interpolation and adaptive networks, Royals Signals and Radar Establishment, 1988, 39 p.
  8. Dinov I.D., Expectation maximization and mixture modeling tutorial, 2008, 18 p.
  9. Ermakov V.V., Bogomolov A., Bykov D.E., Oil sludge depository assessment using multivariate data analysis, Journal of environmental management, 2012, Vol. 105, pp. 144–151.
  10. Mahalanobis P.C., On the generalized distance in statistics, Proceedings of the National Institute of Sciences of India, 1936, Vol. 2, No. 1, pp. 49–55.
  11. Manolakis D., Marden D., Shaw G.A., Hyperspectral image processing for automatic target detection applications, Lincoln Laboratory Journal, 2003, Vol. 14, No. 1, pp. 79–116.
  12. Orr M.J.L., Introduction to radial basis function networks, URL: https://www.cc.gatech.edu/~isbell/tutorials/rbf-intro.pdf (date of the application: 12.01.2017).
  13. Quinlan J.R., Induction of decision trees, Machine learning, 1986, No. 1, pp. 81–106.
  14. Quinlan J.R., C4.5: Programs for Machine Learning, Elsevier, 2014.
  15. Redner R.A., Walker H.F., Mixture densities, maximum likelihood and the em algorithm, SIAM review, 1984, Vol. 26, No. 2, pp. 195–239.