Journal of Siberian Federal University. Engineering & Technologies / The Cluster Analysis and Classification with Training of Multispectral Data of Earth Remote Sensing

Full text (.pdf)
Issue
Journal of Siberian Federal University. Engineering & Technologies. 2009 2 (1)
Authors
Asmus, Vasily V.; Buchnev, Alexey A.; Pyuatkin, Valery P.
Contact information
Asmus, Vasily V. 7 Bolshoy Predtechensky, Moscow, 123242 Russia; Buchnev, Alexey A. 6 pr. Ak. Lavrentjeva, Novosibirsk, 630090 Russia; Pyuatkin, Valery P. 6 pr. Ak. Lavrentjeva, Novosibirsk, 630090 Russia pvp@ooi.sscc.ru
Keywords
Earth remote sensing; data recognition; supervised classification; unsupervised classification; cluster analysis; decision rule; classifier training; K-means method; multidimensional histogram
Abstract

It is obtained questions, connected with the problem of choosing appropriate algorithms of recognition of multispectral data of Earth remote sensing. It is submitted the system of supervised classification, based on a strategy of maximum probability for vectors of indications having the normal distribution. It is described the system of cluster analysis, including an algorithm for K-means method and analyzing method of mode of multidimensional histogram.

Pages
23-31
Paper at repository of SibFU
https://elib.sfu-kras.ru/handle/2311/1278

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).

Меню