Comparison of various image fusion methods for impervious surface classification from VNREDSat-1

TL;DR

This paper compares five multi-resolution image fusion techniques to improve urban impervious surface classification from VNREDSat-1 data, highlighting UNB and Wavelet methods as most effective.

Contribution

It evaluates and identifies the most suitable image fusion methods for accurate impervious surface mapping using VNREDSat-1 imagery.

Findings

UNB method yields the best classification accuracy.

Wavelet transform best preserves spectral information.

UNB performs well in shadowed areas.

Abstract

Impervious surface is an important indicator for urban development monitoring. Accurate urban impervious surfaces mapping with VNREDSat-1 remains challenging due to their spectral diversity not captured by individual PAN image. In this artical, five multi-resolution image fusion techniques were compared for classification task of urban impervious surface. The result shows that for VNREDSat-1 dataset, UNB and Wavelet tranform methods are the best techniques reserving spatial and spectral information of original MS image, respectively. However, the UNB technique gives best results when it comes to impervious surface classification especially in the case of shadow area included in non-impervious surface group.