Subspace-Based Feature Fusion From Hyperspectral And Multispectral Image For Land Cover Classification

TL;DR

This paper introduces a novel subspace-based feature fusion method combining hyperspectral and multispectral images to enhance land cover classification accuracy, addressing performance degradation in conventional fusion techniques.

Contribution

The paper proposes a new feature fusion approach using subspace modeling and optimization algorithms, improving classification performance over existing methods.

Findings

Competitive performance compared to other feature extraction methods

Effective fusion of HS and MS images for land cover classification

Algorithm based on AO and ADMM efficiently solves the fusion problem

Abstract

In remote sensing, hyperspectral (HS) and multispectral (MS) image fusion have emerged as a synthesis tool to improve the data set resolution. However, conventional image fusion methods typically degrade the performance of the land cover classification. In this paper, a feature fusion method from HS and MS images for pixel-based classification is proposed. More precisely, the proposed method first extracts spatial features from the MS image using morphological profiles. Then, the feature fusion model assumes that both the extracted morphological profiles and the HS image can be described as a feature matrix lying in different subspaces. An algorithm based on combining alternating optimization (AO) and the alternating direction method of multipliers (ADMM) is developed to solve efficiently the feature fusion problem. Finally, extensive simulations were run to evaluate the performance of the proposed feature fusion approach for two data sets. In general, the proposed approach exhibits a competitive performance compared to other feature extraction methods.