Hyperspectral Image Super-Resolution Based on Spatial Group Sparsity Regularization Unmixing

Jian Long,Jun Li,Longlong Zhang,Tian Jiang,Yuanxi Peng

doi:10.3390/app10165583

Abstract

A hyperspectral image (HSI) contains many narrow spectral channels, thus containing efficient information in the spectral domain. However, high spectral resolution usually leads to lower spatial resolution as a result of the limitations of sensors. Hyperspectral super-resolution aims to fuse a low spatial resolution HSI with a conventional high spatial resolution image, producing an HSI with high resolution in both the spectral and spatial dimensions. In this paper, we propose a spatial group sparsity regularization unmixing-based method for hyperspectral super-resolution. The hyperspectral image (HSI) is pre-clustered using an improved Simple Linear Iterative Clustering (SLIC) superpixel algorithm to make full use of the spatial information. A robust sparse hyperspectral unmixing method is then used to unmix the input images. Then, the endmembers extracted from the HSI and the abundances extracted from the conventional image are fused. This ensures that the method makes full use of the spatial structure and the spectra of the images. The proposed method is compared with several related methods on public HSI data sets. The results demonstrate that the proposed method has superior performance when compared to the existing state-of-the-art.

Highlights

Hyperspectral imagery (HSI) can profile materials and organisms due to hundreds of narrow spectral bands that correspond to different wavelengths, which is not provided by traditional images
We present and analyze the performance of the proposed hyperspectral image (HSI) super-resolution method
This paper proposed an HSI super-resolution method based on spatial group sparsity regularization unmixing

Summary

Introduction

Hyperspectral imagery (HSI) can profile materials and organisms due to hundreds of narrow spectral bands that correspond to different wavelengths, which is not provided by traditional images. Constrained by sensor technology, the current HSIs usually have low spatial resolution [7] and suffer from the spectral mixing effect, which leads to every single pixel consisting of spectra from several materials. This makes the exploitation of hyperspectral images a big challenge, which is difficult to overcome due to physical limits. Unmixing-based [12,13] unmix the latent HSI into endmember and abundance matrices and constrain the appropriate structures for those factored matrices to regularize the super-resolution problem. In the HSI super-resolution method proposed in this paper, we unmix the low spatial resolution.

Related Work

Problem Formulation

Problem Solution

Experiments

Data Sets and Quantitative Metrics

Experimental Setting

Results and Analysis

Hyperspectral Unmixing

Super-Resolution

Methods

Impact on Classification

Computational Cost