TY - JOUR

T1 - Analysis of the efficiency of classification of hyperspectral satellite images of natural and man-made areas

AU - Borzov, S. M.

AU - Potaturkin, A. O.

AU - Potaturkin, O. I.

AU - Fedotov, A. M.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - The efficiency of a number of the classical methods of supervised classification of hyperspectral data is estimated by an example of discriminating the types of the underlying surface in natural and man-made areas. The minimum distance, support vector machine, Mahalanobis, and maximum likelihood methods are considered. Particular attention is paid to studying the dependence of the data classification accuracy on the number of spectral features and the way of choosing them in the above-mentioned methods. Experimental results obtained by processing real hyperspectral images of landscapes of various types are reported.

AB - The efficiency of a number of the classical methods of supervised classification of hyperspectral data is estimated by an example of discriminating the types of the underlying surface in natural and man-made areas. The minimum distance, support vector machine, Mahalanobis, and maximum likelihood methods are considered. Particular attention is paid to studying the dependence of the data classification accuracy on the number of spectral features and the way of choosing them in the above-mentioned methods. Experimental results obtained by processing real hyperspectral images of landscapes of various types are reported.

KW - classification of surface types

KW - hyperspectral images

KW - reflection spectrum

KW - remote sensing

UR - http://www.scopus.com/inward/record.url?scp=84969802383&partnerID=8YFLogxK

U2 - 10.3103/S8756699016010015

DO - 10.3103/S8756699016010015

M3 - Article

AN - SCOPUS:84969802383

VL - 52

JO - Optoelectronics, Instrumentation and Data Processing

JF - Optoelectronics, Instrumentation and Data Processing

SN - 8756-6990

IS - 1

ER -