Classification of Hyperspectral Images with Different Methods of Training Set Formation
- Autores: Borzov S.M.1, Potaturkin O.I.1,2
-
Afiliações:
- Institute of Automation and Electrometry, Siberian Branch
- Novosibirsk State University
- Edição: Volume 54, Nº 1 (2018)
- Páginas: 76-82
- Seção: Analysis and Synthesis of Signals and Images
- URL: https://journals.rcsi.science/8756-6990/article/view/212366
- DOI: https://doi.org/10.3103/S8756699018010120
- ID: 212366
Citar
Resumo
The efficiency of the methods of controlled spectral and spectral-spatial classification of vegetation types on the basis of hyperspectral pictures with different methods of training set formation is evaluated. The dependence of the classification accuracy on the number of spectral features is considered. It is shown that simultaneous allowance for spatial and spectral features ensures highquality classification of similarly looking types of vegetation by merely using training sets with the maximum degree of the pixel distribution over the image.
Sobre autores
S. Borzov
Institute of Automation and Electrometry, Siberian Branch
Autor responsável pela correspondência
Email: borzov@iae.nsk.su
Rússia, pr. Akademika Koptyuga 1, Novosibirsk, 630090
O. Potaturkin
Institute of Automation and Electrometry, Siberian Branch; Novosibirsk State University
Email: borzov@iae.nsk.su
Rússia, pr. Akademika Koptyuga 1, Novosibirsk, 630090; ul. Pirogova 2, Novosibirsk, 630090
Arquivos suplementares
