Class Signature-Constrained Background- Suppressed Approach to Band Selection for Classification of Hyperspectral Images
- 12 November 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 57 (1) , 14-31
Abstract
In hyperspectral image classification (HSIC), background (BKG) is generally excluded from consideration due to the fact that obtaining complete knowledge of BKG is nearly impossible in reality. Unfortunately, BKG has significant impact on classification and band selection (BS). This paper investigates both issues and presents a novel approach called class signature-constrained BKG suppression (CSCBS) approach to BS for HSIC, where class signatures can be obtained either by a priori or a posteriori knowledge or training samples, and BKG suppression can be accomplished by taking the inverse of the sample correlation matrix R. Its idea takes advantage of the concept of the linearly constrained minimum variance (LCMV) developed from adaptive beamforming by constraining class signatures of interest while minimizing the effect caused by the unknown BKG so as to enhance the classification performance. There are two immediate applications of CSCBS. One is its application to HSIC, in which it becomes a CSCBS classifier. The other is its use of the LCMV-suppressed BKG as a measure to derive the band prioritization (BP) criteria and BS. Experimental results demonstrate that generally CSCBS does not need the full-band set for HSIC since a partial band subset selected by CSCBS-BP/BS can actually improve the classification results using full-band information.Keywords
Funding Information
- Natural Science Foundation of Liaoning Province (20170540095)
- Fundamental Research Funds for the Central Universities (3132018196)
- Chinese Academy of Sciences (LSIT201707D)
- National Natural Science Foundation of China (61601077)
- Fundamental Research Funds for the Central Universities (3132017124)
- Fundamental Research Funds for Central Universities (3132016331, ZD20180073)
This publication has 74 references indexed in Scilit:
- Advances in Hyperspectral Image Classification: Earth Monitoring with Statistical Learning MethodsIEEE Signal Processing Magazine, 2013
- Hyperspectral band clustering and band selection for urban land cover classificationGeocarto International, 2012
- Band Selection for Dimension Reduction in Hyper Spectral Image Using Integrated InformationGain and Principal Components Analysis TechniqueInternational Journal of Machine Learning and Computing, 2012
- Band Selection Based on Feature Weighting for Classification of Hyperspectral DataIEEE Geoscience and Remote Sensing Letters, 2005
- Methodology for Hyperspectral Band SelectionPhotogrammetric Engineering & Remote Sensing, 2004
- Estimation of Number of Spectrally Distinct Signal Sources in Hyperspectral ImageryIEEE Transactions on Geoscience and Remote Sensing, 2004
- Target signature-constrained mixed pixel classification for hyperspectral imageryIEEE Transactions on Geoscience and Remote Sensing, 2002
- A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classificationIEEE Transactions on Geoscience and Remote Sensing, 1999
- Floating search methods in feature selectionPattern Recognition Letters, 1994
- Selection of optimum bands from TM scenes through mutual information analysisISPRS Journal of Photogrammetry and Remote Sensing, 1993