The impact of band selection on gas detection algorithms

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-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 languageEnglish
Title of host publicationImaging Spectrometry XV
DOIs
StatePublished - 19 Oct 2010
EventImaging Spectrometry XV - San Diego, CA, United States
Duration: 2 Aug 20103 Aug 2010

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume7812
ISSN (Print)0277-786X

Conference

ConferenceImaging Spectrometry XV
Country/TerritoryUnited States
CitySan Diego, CA
Period2/08/103/08/10

Keywords

  • Band selection
  • Gas detection
  • Hyperspectral

Fingerprint

Dive into the research topics of 'The impact of band selection on gas detection algorithms'. Together they form a unique fingerprint.

Cite this