Share Email Print

Proceedings Paper

Selection of spectral bands for interpretation of hyperspectral remotely sensed images
Author(s): Patrick F. Valdez; Gregory W. Donohoe; Michael R. Descour; Sheila E. Motomatsu
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Technological improvements in optical sensors have resulted in the collection of spectral information across hundreds of very narrow bands thereby giving analysts detailed spectral signatures not available a few years ago. While useful for identifying materials in a laboratory, the detailed spectral signatures of current hyperspectral sensors present much more information than required for discrimination between materials on the Earth's surface. The sheer volume of spectral information can be overwhelming and has lead to research efforts aimed at selecting only those features useful for the task at hand. In this paper, a method based on maximizing the Bhattacharyya distance to select an optimal subset of spectral bands is presented and applied in discriminating between several mineral classes from the USGS Spectral Library database.

Paper Details

Date Published: 13 November 1996
PDF: 9 pages
Proc. SPIE 2819, Imaging Spectrometry II, (13 November 1996); doi: 10.1117/12.258066
Show Author Affiliations
Patrick F. Valdez, Univ. of New Mexico (United States)
Gregory W. Donohoe, Univ. of New Mexico (United States)
Michael R. Descour, Optical Sciences Ctr./Univ. of Arizona (United States)
Sheila E. Motomatsu, Sandia National Labs. (United States)

Published in SPIE Proceedings Vol. 2819:
Imaging Spectrometry II
Michael R. Descour; Jonathan Martin Mooney, Editor(s)

© SPIE. Terms of Use
Back to Top