DocumentCode
2974466
Title
A neural approach to classification of satellite images
Author
Diverio, Viviane Todt ; Gomez, Arthur TÓrgo ; OsÓrio, Fernando Santos ; Hoffmann, Leandro Toss ; Rodrigues, AntÔnio Gabriel
Author_Institution
Lab. de Sensoriamento Remoto e Cartografia, Univ. do Vale do Rio dos Sinos, Sao Leopoldo, Brazil
fYear
2002
fDate
2002
Firstpage
413
Abstract
This paper shows the results obtained using a traditional statistical method (Gaussian Maximum Likelihood) and artificial neural networks (backpropagation and cascade-correlation) applied to multispectral Landsat Thematic Mapper data classification. The studied images cover a region situated in Rio Grande do Sul State Brazil.
Keywords
backpropagation; geography; image classification; maximum likelihood estimation; neural nets; Gaussian Maximum Likelihood; artificial neural networks; backpropagation neural network; cascade-correlation neural network; data classification; multispectral Landsat Thematic Mapper; satellite image classification; statistical method; Artificial neural networks; Costs; Data acquisition; Databases; Planets; Radio access networks; Remote monitoring; Remote sensing; Satellites; Statistical analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Graphics and Image Processing, 2002. Proceedings. XV Brazilian Symposium on
ISSN
1530-1834
Print_ISBN
0-7695-1846-X
Type
conf
DOI
10.1109/SIBGRA.2002.1167185
Filename
1167185
Link To Document