Standard

Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data. / Borzov, Sergey Mihaylovich; Guryanov, Mark Aleksandrovich; Potaturkin, O. I.

In: Computer Optics, Vol. 43, No. 3, 01.05.2019, p. 464-473.

Research output: Contribution to journal › Article › peer-review

Harvard

Borzov, SM, Guryanov, MA & Potaturkin, OI 2019, 'Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data', Computer Optics, vol. 43, no. 3, pp. 464-473. https://doi.org/10.18287/2412-6179-2019-43-3-464-473

APA

Borzov, S. M., Guryanov, M. A., & Potaturkin, O. I. (2019). Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data. Computer Optics, 43(3), 464-473. https://doi.org/10.18287/2412-6179-2019-43-3-464-473

Vancouver

Borzov SM, Guryanov MA, Potaturkin OI. Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data. Computer Optics. 2019 May 1;43(3):464-473. doi: 10.18287/2412-6179-2019-43-3-464-473

Author

Borzov, Sergey Mihaylovich ; Guryanov, Mark Aleksandrovich ; Potaturkin, O. I. / Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data. In: Computer Optics. 2019 ; Vol. 43, No. 3. pp. 464-473.

BibTeX

@article{8f79fa2bd3e547e0a593ed38444d8b0f,
title = "Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data",
abstract = "The article is devoted to the effectiveness research of methods of controlled spectral and spectral-spatial classification of hyperspectral data. In particular, minimum distance, support vector machine, mahalanobis distance and maximum likelihood methods are considered on the example of vegetative cover types differentiation. Significant attention is paid to studying the dependence of the accuracy of data classification with listed methods on the spectral features number and their selection method. The perspectivity of complex processing of spectral and spatial features, considering the correlation of close pixels, is demonstrated. The experimental results obtained with various methods of forming training sets are presented.",
keywords = "Cover types classification, Hyperspectral images, Image processing, Remote sensing, Spectral and spatial features",
author = "Borzov, {Sergey Mihaylovich} and Guryanov, {Mark Aleksandrovich} and Potaturkin, {O. I.}",
note = "Publisher Copyright: {\textcopyright} 2019, Institution of Russian Academy of Sciences. All rights reserved. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.",
year = "2019",
month = may,
day = "1",
doi = "10.18287/2412-6179-2019-43-3-464-473",
language = "English",
volume = "43",
pages = "464--473",
journal = "Computer Optics",
issn = "0134-2452",
publisher = "Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS",
number = "3",

}

RIS

TY - JOUR

T1 - Study of the classification efficiency of difficult-to-distinguish vegetation types using hyperspectral data

AU - Borzov, Sergey Mihaylovich

AU - Guryanov, Mark Aleksandrovich

AU - Potaturkin, O. I.

N1 - Publisher Copyright: © 2019, Institution of Russian Academy of Sciences. All rights reserved. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2019/5/1

Y1 - 2019/5/1

N2 - The article is devoted to the effectiveness research of methods of controlled spectral and spectral-spatial classification of hyperspectral data. In particular, minimum distance, support vector machine, mahalanobis distance and maximum likelihood methods are considered on the example of vegetative cover types differentiation. Significant attention is paid to studying the dependence of the accuracy of data classification with listed methods on the spectral features number and their selection method. The perspectivity of complex processing of spectral and spatial features, considering the correlation of close pixels, is demonstrated. The experimental results obtained with various methods of forming training sets are presented.

AB - The article is devoted to the effectiveness research of methods of controlled spectral and spectral-spatial classification of hyperspectral data. In particular, minimum distance, support vector machine, mahalanobis distance and maximum likelihood methods are considered on the example of vegetative cover types differentiation. Significant attention is paid to studying the dependence of the accuracy of data classification with listed methods on the spectral features number and their selection method. The perspectivity of complex processing of spectral and spatial features, considering the correlation of close pixels, is demonstrated. The experimental results obtained with various methods of forming training sets are presented.

KW - Cover types classification

KW - Hyperspectral images

KW - Image processing

KW - Remote sensing

KW - Spectral and spatial features

UR - http://www.scopus.com/inward/record.url?scp=85070460263&partnerID=8YFLogxK

U2 - 10.18287/2412-6179-2019-43-3-464-473

DO - 10.18287/2412-6179-2019-43-3-464-473

M3 - Article

AN - SCOPUS:85070460263

VL - 43

SP - 464

EP - 473

JO - Computer Optics

JF - Computer Optics

SN - 0134-2452

IS - 3

ER -

ID: 25325352