Title :
The analysis of satellite data of remote Earth sensing
Author :
Vladimirov, V.M. ; Karmishin, A.M. ; Sharova, L.I. ; Sharova, T.V.
Author_Institution :
Dept. of Radiotech. & Electron., Krasnoyarsk Sci. Center, Russia
Abstract :
In the paper methods of processing spectrozonal images, obtained with the scanner systems of the “Resurs 01-3” satellite, are considered. The analysis using artificial neutral networks to estimate parameters and a classification of Earth surface types from the results of satellite measurements has been made. As an example, use has been made of space images of Yugoslavia, obtained with the Russian scanners of medium MSU-SK and high MSU-E resolution, allowing the Earth image to be obtained for MSU-SK in the five spectral ranges of 0.54-0.6; 0.6-0.7; 0.7-0.8; 0.8-1.0; 10.3-11.75 μm, and for MSU-E in the three spectral ranges of 0.5-0.6; 0.6-0.7 and 0.8-0.9 μm with spatial resolution order of 30-45 m
Keywords :
geophysical signal processing; image classification; neural nets; parameter estimation; remote sensing; 0.5 to 11.75 mum; Earth surface types; Resurs 01-3 satellite; Yugoslavia; artificial neutral networks; classification; parameters estimation; remote Earth sensing; satellite data; space images; spectral ranges; spectrozonal image; Artificial satellites; Data analysis; Data processing; Earth; Geology; Image resolution; Neural networks; Packaging; Parameter estimation; Satellite broadcasting;
Conference_Titel :
Telecommunications in Modern Satellite, Cable and Broadcasting Services, 1999. 4th International Conference on
Conference_Location :
Nis
Print_ISBN :
0-7803-5768-X
DOI :
10.1109/TELSKS.1999.806242