Deep Learning for Classification of Hyperspectral Data: A Comparative Review

In recent years, deep-learning techniques revolutionized the way remote sensing data are processed. The classification of hyperspectral data is no exception to the rule, but it has intrinsic specificities that make the application of deep learning less straightforward than with other optical data. T...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing magazine Vol. 7; no. 2; pp. 159 - 173
Main Authors: Audebert, Nicolas, Le Saux, Bertrand, Lefevre, Sebastien
Format: Journal Article
Language:English
Published: IEEE 01.06.2019
Subjects:
Computer Science
Computer Vision and Pattern Recognition
Deep learning
Hyperspectral imaging
Machine learning
Neural and Evolutionary Computing
Sensors
Spatial resolution
ISSN:2473-2397, 2168-6831
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, deep-learning techniques revolutionized the way remote sensing data are processed. The classification of hyperspectral data is no exception to the rule, but it has intrinsic specificities that make the application of deep learning less straightforward than with other optical data. This article presents the state of the art of previous machine-learning approaches, reviews the various deeplearning approaches currently proposed for hyperspectral classification, and identifies the problems and difficulties that arise in the implementation of deep neural networks for this task. In particular, the issues of spatial and spectral resolution, data volume, and transfer of models from multimedia images to hyperspectral data are addressed. Additionally, a comparative study of various families of network architectures is provided, and a software toolbox is publicly released to allow experimenting with these methods (https://github.com/nshaud/DeepHyperX). This article is intended for both data scientists with interest in hyperspectral data and remote sensing experts eager to apply deeplearning techniques to their own data set.
ISSN:2473-2397
2168-6831
DOI:10.1109/MGRS.2019.2912563