Skip to main navigation Skip to search Skip to main content

Unsupervised band selection method based on improved N-FINDR algorithm for spectral unmixing

  • Liguo Wang*
  • , Ye Zhang
  • , Yanfeng Gu
  • *Corresponding author for this work
  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Hyperspectral imagery (HSI) has high spectral dimensionality which presents a serious challenge to HSI processing, and so reduction of dimensionality is necessary. Band selection (BS) is one of the categories of dimensionality reduction methods. Existing BS methods have expensive cost, need prior information or only cater for classification. In order to get an efficient and unsupervised BS method for spectral unmixing, two aspects work are done. First, original N-FINDR algorithm is greatly improved by substituting volume calculation for distance test. Second, the improved N-FINDR algorithm is used to construct an unsupervised BS method for spectral unmixing. Both theory and experiments prove that the new unsupervised BS method is very effective.

Original languageEnglish
Title of host publication1st International Symposium on Systems and Control in Aerospace and Astronautics
PublisherIEEE Computer Society
Pages1018-1021
Number of pages4
ISBN (Print)0780393953, 9780780393950
StatePublished - 2006
Event1st International Symposium on Systems and Control in Aerospace and Astronautics - Harbin, China
Duration: 19 Jan 200621 Jan 2006

Publication series

Name1st International Symposium on Systems and Control in Aerospace and Astronautics
Volume2006

Conference

Conference1st International Symposium on Systems and Control in Aerospace and Astronautics
Country/TerritoryChina
CityHarbin
Period19/01/0621/01/06

Fingerprint

Dive into the research topics of 'Unsupervised band selection method based on improved N-FINDR algorithm for spectral unmixing'. Together they form a unique fingerprint.

Cite this