The impact of band selection on gas detection algorithms

S. R. Rotman; N. Bar-Zeev; L. Stern

doi:10.1117/12.859071

The impact of band selection on gas detection algorithms

S. R. Rotman, N. Bar-Zeev, L. Stern

Department of Electrical & Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

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.

Original language	English
Title of host publication	Imaging Spectrometry XV
DOIs	https://doi.org/10.1117/12.859071
State	Published - 19 Oct 2010
Event	Imaging Spectrometry XV - San Diego, CA, United States Duration: 2 Aug 2010 → 3 Aug 2010

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	7812
ISSN (Print)	0277-786X

Conference

Conference	Imaging Spectrometry XV
Country/Territory	United States
City	San Diego, CA
Period	2/08/10 → 3/08/10

Keywords

Band selection
Gas detection
Hyperspectral

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.859071

Cite this

@inproceedings{b39004d122654309bb5bdea8309545c7,

title = "The impact of band selection on gas detection algorithms",

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.",

keywords = "Band selection, Gas detection, Hyperspectral",

author = "Rotman, {S. R.} and N. Bar-Zeev and L. Stern",

year = "2010",

month = oct,

day = "19",

doi = "10.1117/12.859071",

language = "English",

isbn = "9780819483089",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

booktitle = "Imaging Spectrometry XV",

note = "Imaging Spectrometry XV ; Conference date: 02-08-2010 Through 03-08-2010",

}

TY - GEN

T1 - The impact of band selection on gas detection algorithms

AU - Rotman, S. R.

AU - Bar-Zeev, N.

AU - Stern, L.

PY - 2010/10/19

Y1 - 2010/10/19

N2 - 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.

AB - 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.

KW - Band selection

KW - Gas detection

KW - Hyperspectral

UR - http://www.scopus.com/inward/record.url?scp=77957880908&partnerID=8YFLogxK

U2 - 10.1117/12.859071

DO - 10.1117/12.859071

M3 - Conference contribution

AN - SCOPUS:77957880908

SN - 9780819483089

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Imaging Spectrometry XV

T2 - Imaging Spectrometry XV

Y2 - 2 August 2010 through 3 August 2010

ER -

The impact of band selection on gas detection algorithms

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this