Classification non supervis{\'e}es d'acquisitions hyperspectrales cod{\'e}es : quelles v{\'e}rit{\'e}s terrain ?

TL;DR

This paper introduces an unsupervised classification method for coded hyperspectral data that identifies classes and estimates spectra despite data compression, while emphasizing the need for better evaluation standards.

Contribution

It presents a novel unsupervised classification approach tailored for coded hyperspectral data with limited acquisitions, addressing intra-class variability and evaluation challenges.

Findings

Method effectively identifies classes and spectra despite data compression.

Highlights limitations of current ground truth evaluation methods.

Demonstrates the approach on Pavia University scene.

Abstract

We propose an unsupervised classification method using a limited number of coded acquisitions from a DD-CASSI hyperspectral imager. Based on a simple model of intra-class spectral variability, this approach allow to identify classes and estimate reference spectra, despite data compression by a factor of ten. Here, we highlight the limitations of the ground truths commonly used to evaluate this type of method: lack of a clear definition of the notion of class, high intra-class variability, and even classification errors. Using the Pavia University scene, we show that with simple assumptions, it is possible to detect regions that are spectrally more coherent, highlighting the need to rethink the evaluation of classification methods, particularly in unsupervised scenarios.