DMCA
RECENT DEVELOPMENTS IN SPARSE HYPERSPECTRAL UNMIXING
| Citations: | 2 - 0 self |
BibTeX
@MISC{Iordache_recentdevelopments,
author = {Marian-daniel Iordache and Antonio Plaza and José Bioucas-dias},
title = {RECENT DEVELOPMENTS IN SPARSE HYPERSPECTRAL UNMIXING},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper explores the applicability of new sparse algorithms to perform spectral unmixing of hyperspectral images using available spectral libraries instead of resorting to well-known endmember extraction techniques widely available in the literature. Our main assumption is that it is unlikely to find pure pixels in real hyperspectral images due to available spatial resolution and mixing phenomena happening at different scales. The algorithms analyzed in our study rely on different principles, and their performance is quantitatively assessed using both simulated and real hyperspectral data sets. The experimental validation of sparse techniques conducted in this work indicates promising results of this new approach to attack the spectral unmixing problem in remotely sensed hyperspectral images. Index Terms — Hyperspectral unmixing, sparse regression, convex optimization, spectral libraries.
Keyphrases
recent development sparse hyperspectral unmixing sparse technique new approach spectral unmixing problem different principle hyperspectral image experimental validation real hyperspectral image main assumption different scale sensed hyperspectral image well-known endmember extraction technique available spectral library real hyperspectral data set sparse regression available spatial resolution new sparse algorithm convex optimization spectral library pure pixel index term hyperspectral unmixing promising result spectral unmixing
