- Issue
- Journal of Siberian Federal University. Engineering & Technologies. 2017 10 (6)
- Authors
- Dmitriev, Egor V.; Kozoderov, Vladimir V.; Dementyev, Alexander O.; Sokolov, Anton A.
- Contact information
- Dmitriev, Egor V.: Institute of Numerical Mathematics RAS 8 Gubkina Str., Moscow, 119333, Russia; ; Kozoderov, Vladimir V.: M.V. Lomonosov Moscow State University 1 Leninskiye Gory, Moscow, 119991, Russia; ; Dementyev, Alexander O.: Institute of Numerical Mathematics RAS 8 Gubkina Str., Moscow, 119333, Russia; Sokolov, Anton A.: Laboratoire de Physico-Chimie de l’Atmosphère Université du Littoral Cote d’Opale, 189A Avenue Maurice Schumann, Dunkerque, 59140, France
- Keywords
- Remote sensing; pattern recognition; spectral classification; hyperspectral measurements
- Abstract
The basic model of the recognition of forest inventory characteristics using spectral features is represented in the framework of the problem of hyperspectral airborne imagery processing. The algorithm of multiclass supervised classification based on the error-correcting output codes underlies this model. The support vector machine method is used as the necessary binary classifier. The method of the construction of training set by using mixed forest plots is represented. Results of the retrieval of species and age composition of forest stands from hyperspectral images are represented for the selected test area. The estimate of accuracy of the retrieval of the mixed forest composition is comparable with the accuracy of ground-based forest inventory data
- Pages
- 794-804
- Paper at repository of SibFU
- https://elib.sfu-kras.ru/handle/2311/35013
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).