DocumentCode
2116886
Title
An unsupervised algorithm for the selection of endmembers in hyperspectral images
Author
Acito, N. ; Corsini, G. ; Diani, M.
Author_Institution
Dipt. di Ingegneria dell´´Informazione, Pisa Univ., Italy
Volume
3
fYear
2002
fDate
24-28 June 2002
Firstpage
1673
Abstract
An efficient algorithm for endmember selection is illustrated. Endmembers are estimated by an unsupervised segmentation procedure based on spectral analysis. Preliminary results obtained on experimental data are presented and discussed.
Keywords
geophysical signal processing; geophysical techniques; image processing; image segmentation; multidimensional signal processing; remote sensing; terrain mapping; vegetation mapping; 400 to 2500 nm; IR; endmember selection; endmembers; geophysical measurement technique; hyperspectral images; hyperspectral remote sensing; image processing; infrared; land surface; multidimensional signal processing; multispectral remote sensing; spectral analysis; terrain mapping; unsupervised algorithm; unsupervised segmentation; vegetation mapping; visible; Background noise; Covariance matrix; Histograms; Hyperspectral imaging; Image segmentation; Layout; Principal component analysis; Spatial resolution; Spectral analysis; Vectors;
fLanguage
English
Publisher
ieee
Conference_Titel
Geoscience and Remote Sensing Symposium, 2002. IGARSS '02. 2002 IEEE International
Print_ISBN
0-7803-7536-X
Type
conf
DOI
10.1109/IGARSS.2002.1026217
Filename
1026217
Link To Document