elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification

Mou, LiChao and Saha, Sudipan and Hua, Yuansheng and Bovolo, Francesca and Bruzzone, Lorenzo and Zhu, Xiao Xiang (2022) Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 60, p. 5504414. IEEE - Institute of Electrical and Electronics Engineers. doi: 10.1109/TGRS.2021.3067096. ISSN 0196-2892.

[img] PDF - Postprint version (accepted manuscript)
9MB

Official URL: https://ieeexplore.ieee.org/document/9387453

Abstract

Band selection refers to the process of choosing the most relevant bands in a hyperspectral image. By selecting a limited number of optimal bands, we aim at speeding up model training, improving accuracy, or both. It reduces redundancy among spectral bands while trying to preserve the original information of the image. By now, many efforts have been made to develop unsupervised band selection approaches, of which the majorities are heuristic algorithms devised by trial and error. In this article, we are interested in training an intelligent agent that, given a hyperspectral image, is capable of automatically learning policy to select an optimal band subset without anyhand-engineered reasoning. To this end, we frame the problem of unsupervised band selection as a Markov decision process, propose an effective method to parameterize it, and finally solve the problem by deep reinforcement learning. Once the agent is trained, it learns a band-selection policy that guides the agent to sequentially select bands by fully exploiting the hyperspectral image and previously picked bands. Furthermore, we propose two different reward schemes for the environment simulation of deep reinforcement learning and compare them in experiments. This, to the best of our knowledge, is the first study that explores a deep reinforcement learning model for hyperspectral image analysis, thus opening a new door for future research and showcasing the great potential of deep reinforcement learning in remote sensing applications. Extensive experiments are carried out on four hyperspectral data sets, and experimental results demonstrate the effectiveness of the proposed method. The code is publicly available.

Item URL in elib:https://elib.dlr.de/146194/
Document Type:Article
Title:Deep Reinforcement Learning for Band Selection in Hyperspectral Image Classification
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Mou, LiChaoLiChao.Mou (at) dlr.dehttps://orcid.org/0000-0001-8407-6413
Saha, Sudipansudipan.saha (at) tum.deUNSPECIFIED
Hua, YuanshengYuansheng.Hua (at) dlr.deUNSPECIFIED
Bovolo, Francescabovolo (at) fbk.euhttps://orcid.org/0000-0003-3104-7656
Bruzzone, Lorenzolorenzo.bruzzone (at) unitn.ithttps://orcid.org/0000-0002-6036-459X
Zhu, Xiao Xiangxiao.zhu (at) dlr.dehttps://orcid.org/0000-0001-5530-3613
Date:2022
Journal or Publication Title:IEEE Transactions on Geoscience and Remote Sensing
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:60
DOI :10.1109/TGRS.2021.3067096
Page Range:p. 5504414
Publisher:IEEE - Institute of Electrical and Electronics Engineers
ISSN:0196-2892
Status:Published
Keywords:Hyperspectral imaging, Task analysis, Reinforcement learning, Markov processes, Earth, Correlation, Feature extraction
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Artificial Intelligence
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Rösel, Anja
Deposited On:26 Nov 2021 09:23
Last Modified:20 Dec 2021 17:48

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.