A Dashboard to Analysis and Synthesis of Dimensionality Reduction Methods in Remote Sensing

TL;DR

This paper surveys various dimensionality reduction methods in hyperspectral image classification, critiques existing approaches, and introduces a dashboard tool to assist users in analyzing feature selection and extraction techniques.

Contribution

It provides a comprehensive survey of dimensionality reduction schemes and presents a novel dashboard for analyzing and synthesizing these methods in remote sensing.

Findings

Identifies redundancy and noise issues in hyperspectral data

Critiques existing feature selection and reduction methods

Proposes a dashboard tool for analysis and synthesis

Abstract

Hyperspectral images (HSI) classification is a high technical remote sensing software. The purpose is to reproduce a thematic map . The HSI contains more than a hundred hyperspectral measures, as bands (or simply images), of the concerned region. They are taken at neighbors frequencies. Unfortunately, some bands are redundant features, others are noisily measured, and the high dimensionality of features made classification accuracy poor. The problematic is how to find the good bands to classify the regions items. Some methods use Mutual Information (MI) and thresholding, to select relevant images, without processing redundancy. Others control and avoid redundancy. But they process the dimensionality reduction, some times as selection, other times as wrapper methods without any relationship . Here , we introduce a survey on all scheme used, and after critics and improvement, we synthesize a dashboard, that helps user to analyze an hypothesize features selection and extraction softwares.