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

Spectral-Spatial Classification Integrating Band Selection for Hyperspectral Imagery With Severe Noise Bands

Zhao, Ji and Tian, Suzheng and Geiß, Christian and Wang, Lizhe and Zhong, Yanfei and Taubenböck, Hannes (2020) Spectral-Spatial Classification Integrating Band Selection for Hyperspectral Imagery With Severe Noise Bands. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, pp. 1597-1609. IEEE - Institute of Electrical and Electronics Engineers. doi: 10.1109/JSTARS.2020.2984568. ISSN 1939-1404.

[img] PDF - Published version
6MB

Official URL: https://ieeexplore.ieee.org/document/9064549

Abstract

Spectral-spatial classification for hyperspectral imagery has been receiving much attention, since the detailed spectral and rich spatial information of hyperspectral images can be fully exploited to improve the classification accuracy. However, when the original hyperspectral images have very noisy bands, these bands may have an unfavorable impact on the classification, and are often discarded in advance based on expert knowledge. In this study, a spectral-spatial conditional random field classification algorithm integrating band selection (CRFBS) is developed for hyperspectral imagery with severe noise bands. The proposed algorithm integrates band selection based on the relative utility of the spectral bands for classification. Consequently, negative effects of severe noise bands are eliminated and the need for high-quality image data is substantially reduced. In addition, the CRFBS algorithm makes comprehensive use of both the spectral and the spatial cues to improve the classification performance. The spectral cues are formulated by integrating the support vector machine and random forest algorithms to improve the spectral discriminative ability in the unary potentials, and the spatial information are modeled to consider the interactions between pixels in pairwise potentials. The experiments using different airborne and UAV-borne hyperspectral data verified the effectiveness of the CRFBS method. The CRFBS algorithm can achieve accurate interpretation of the various classification categories and a more than 3% improvement in classification accuracy, compared with the method using the original hyperspectral image with severe noise bands.

Item URL in elib:https://elib.dlr.de/135031/
Document Type:Article
Title:Spectral-Spatial Classification Integrating Band Selection for Hyperspectral Imagery With Severe Noise Bands
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Zhao, JiChina University of Geosciences, WuhanUNSPECIFIED
Tian, SuzhengChina University of Geosciences, WuhanUNSPECIFIED
Geiß, ChristianChristian.Geiss (at) dlr.deUNSPECIFIED
Wang, LizheWuhan University, Wuhan, ChinaUNSPECIFIED
Zhong, YanfeiWuhan University, Wuhan, ChinaUNSPECIFIED
Taubenböck, Hanneshannes.taubenboeck (at) dlr.dehttps://orcid.org/0000-0003-4360-9126
Date:2020
Journal or Publication Title:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Refereed publication:Yes
Open Access:Yes
Gold Open Access:Yes
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:13
DOI :10.1109/JSTARS.2020.2984568
Page Range:pp. 1597-1609
Publisher:IEEE - Institute of Electrical and Electronics Engineers
ISSN:1939-1404
Status:Published
Keywords:Conditional random fields, hyperspectral image, image classification, random forest, spectral-spatial classification
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 - Remote Sensing and Geo Research
Location: Oberpfaffenhofen
Institutes and Institutions:German Remote Sensing Data Center > Geo Risks and Civil Security
Deposited By: Taubenböck, Dr. Hannes
Deposited On:03 Jun 2020 11:03
Last Modified:24 Nov 2020 04:13

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.