Share Email Print

Proceedings Paper

The impact of band selection on gas detection algorithms
Author(s): S. R. Rotman; N. Bar-Zeev; L. Stern
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A new method is developed for evaluating band selection for detecting gases in hyperspectral images. We use a no-gas background to estimate the sample correlation matrix; we detect anomalies in the gas-present image. After separating the gas and background pixels, we then calculate the SNR. We find that increasing the number of bands tends to lower our overall performance.

Paper Details

Date Published: 13 August 2010
PDF: 7 pages
Proc. SPIE 7812, Imaging Spectrometry XV, 78120A (13 August 2010); doi: 10.1117/12.859071
Show Author Affiliations
S. R. Rotman, Ben-Gurion Univ. of the Negev (Israel)
N. Bar-Zeev, Ben-Gurion Univ. of the Negev (Israel)
L. Stern, Ben-Gurion Univ. of the Negev (Israel)

Published in SPIE Proceedings Vol. 7812:
Imaging Spectrometry XV
Sylvia S. Shen; Paul E. Lewis, Editor(s)

© SPIE. Terms of Use
Back to Top