Multispectral image classification using generalized Fully Constrained Least Squares approach

Ren Jie Yang, Hsuan Ren

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

2 Scopus citations

Abstract

Fully Constrained Least Squares (FCLS) has been widely used and proven to be a powerful tool for hyperspectral image classification. But for multispectral remote sensing images with only a few bands, the Least-Squares based approaches will all encounter the band number constraint (BNC), which requires the number of bands should be no less than the number of classes. In this paper, we proposed a generalization of the FCLS called generalized FCLS (GFCLS) that relaxes this constraint in such a manner that the FCLS can be extended to multispectral image processing in a supervised fashion. The idea of the GFCLS is to create a new set of additional bands that are generated nonlinearly from original multispectral bands prior to the FCLS classification. The effectiveness of the proposed GFCLS is evaluated by SPOT-5 images. Experimental results show that the generalized FCLS (GFCLS) method outperforms the conventional FCLS approach for multispectral imagery classification.

Original languageEnglish
Title of host publication29th Asian Conference on Remote Sensing 2008, ACRS 2008
Pages1698-1703
Number of pages6
StatePublished - 2008
Event29th Asian Conference on Remote Sensing 2008, ACRS 2008 - Colombo, Sri Lanka
Duration: 10 Nov 200814 Nov 2008

Publication series

Name29th Asian Conference on Remote Sensing 2008, ACRS 2008
Volume3

Conference

Conference29th Asian Conference on Remote Sensing 2008, ACRS 2008
Country/TerritorySri Lanka
CityColombo
Period10/11/0814/11/08

Keywords

  • Band generation process (BGP)
  • Generalized Fully Constrained Least Squares (GFCLS)
  • Orthogonal subspace projection (OSP)
  • Target generation process (TGP)

Fingerprint

Dive into the research topics of 'Multispectral image classification using generalized Fully Constrained Least Squares approach'. Together they form a unique fingerprint.

Cite this