Semisupervised Hyperspectral Band Selection Via Spectral–Spatial Hypergraph Model

Band selection is an essential step toward effective and efficient hyperspectral image classification. Traditional supervised band selection methods are often hindered by the problem of lacking enough training samples. To address this problem, we propose a semisupervised band selection method that allows contribution from both labeled and unlabeled hyperspectral pixels. This method first builds a hypergraph model from all hyperspectral samples to measure the similarity among pixels. We show that hypergraph can capture relationship among pixels in both spectral and spatial domain. In the second step, a semisupervised learning method is introduced to propagate class labels to unlabeled samples. Then a linear regression model with group sparsity constraint is used for band selection. Finally, hyperspectral pixels with selected bands are used to train a support vector machine (SVM) classifier. The proposed method is tested on three benchmark datasets. Experimental results demonstrate its advantages over several other band selection methods.

I Introduction

Hyperspectral imagery has been used in a variety of remote sensing applications. It contains hundreds of spectral bands with nanoscale spectral resolution, which provides valuable information for target detection and classification. However, such abundant wavelength indexed bands also contain redundant or correlated information, which influence the effectiveness and efficiency of data modeling [1]. An intuitive way of solving this problem is selecting a subset of bands from the original data [2].