DocumentCode
2137342
Title
Land cover classification from hyperspectral remotely sensed data: an investigation of spectral, spatial and noise issues
Author
Foody, Giles M. ; Sargent, Isabel M J ; Atkinson, Peter M. ; Williams, John W.
Author_Institution
Dept. of Geogr., Southampton Univ., UK
Volume
6
fYear
2001
fDate
2001
Firstpage
2728
Abstract
The effect of spatial, spectral and noise degradations on the accuracy of two thematic labelling scenarios with hyperspectral data was investigated. Although all of the degradations significantly influenced accuracy, the noise content of the data was consistently noted as a major variable affecting the accuracy of both supervised classification and sub-pixel anomaly detection analyses
Keywords
image classification; vegetation mapping; degradations; hyperspectral remotely sensed data; land cover classification; noise issues; spatial issues; spectral issues; sub-pixel anomaly detection analyses; supervised classification; thematic labelling scenarios; Degradation; Feature extraction; Geography; Hyperspectral imaging; Hyperspectral sensors; Labeling; Layout; Pixel; Remote sensing; Spectroscopy;
fLanguage
English
Publisher
ieee
Conference_Titel
Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International
Conference_Location
Sydney, NSW
Print_ISBN
0-7803-7031-7
Type
conf
DOI
10.1109/IGARSS.2001.978143
Filename
978143
Link To Document