Selection of spectral bands for interpretation of hyperspectral remotely sensed images

Patrick F. Valdez; Gregory W. Donohoe; Michael R. Descour; Sheila E. Motomatsu

doi:10.1117/12.258066

13 November 1996 Selection of spectral bands for interpretation of hyperspectral remotely sensed images

Patrick F. Valdez, Gregory W. Donohoe, Michael R. Descour, Sheila E. Motomatsu

Proceedings Volume 2819, Imaging Spectrometry II; (1996) https://doi.org/10.1117/12.258066
Event: SPIE's 1996 International Symposium on Optical Science, Engineering, and Instrumentation, 1996, Denver, CO, United States

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.

Citation Download Citation

Patrick F. Valdez, Gregory W. Donohoe, Michael R. Descour, and Sheila E. Motomatsu "Selection of spectral bands for interpretation of hyperspectral remotely sensed images", Proc. SPIE 2819, Imaging Spectrometry II, (13 November 1996); https://doi.org/10.1117/12.258066

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available