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

Development of a new spectral library classifier for airborne hyperspectral images on heterogeneous environments

Mende, Andre and Heiden, Uta and Bachmann, Martin and Hoja, Danielle and Buchroithner, Manfred (2011) Development of a new spectral library classifier for airborne hyperspectral images on heterogeneous environments. In: Proceedings of the EARSeL 7th SIG-Imaging Spectroscopy Workshop, pp. 1-9. EARSeL 7th SIG-Imaging Spectroscopy Workshop, 11.-13. April 2011, Edinburgh, United Kingdom.

[img]
Preview
PDF
974kB

Abstract

The classification of hyperspectral images on heterogeneous environments without prior knowledge about the study area is a challenging task. Finding potential pure spectral signatures or endmembers (EM) of the various surface materials within an image is essential for obtaining accurate classification results. Automated endmember selection techniques, in many cases, return an unlabelled result without a relationship to a known material. This study demonstrates the potential of an automated spectral classification approach for hyperspectral imagery by using a comprehensive spectral library including a generalized class structure without the use of prior knowledge of the given scene. The classifier works by comparing every unknown image pixel to all labelled known spectra in the spectral library using a mixed measure similarity analysis of the spectral information divergence SID (Chang, 2000), the spectral angle mapper SAM (Kruse et. al., 1993) and the tangent trigonometric function (Du et. al., 2004). These similarity measures are the main criteria used to assign the class membership to a given pixel. In addition, a statistical analysis of the best ten scores identifies the statistical dominant material class from the similarity analysis. This statistical approach allows a pixel-related estimation of the classification reliability. The spectral library comparison classifier (SLC-Classifier) enables the classification of hyperspectral images on heterogeneous environments to be as complete as possible (depends on the input spectral library) with results containing both labelled potential pure spectra and spectra with low similarity agreement. Pixels with low similarity agreement are mixed pixels and pixels related to materials without good representative spectra in the comprehensive spectral library. We demonstrate that this classifier is suitable for the identification of surface materials using hyperspectral images were detailed knowledge about the environments does not exist.

Item URL in elib:https://elib.dlr.de/72268/
Document Type:Conference or Workshop Item (Paper, Poster)
Title:Development of a new spectral library classifier for airborne hyperspectral images on heterogeneous environments
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Mende, AndreTU DresdenUNSPECIFIED
Heiden, Utauta.heiden (at) dlr.deUNSPECIFIED
Bachmann, Martinmartin.bachmann (at) dlr.deUNSPECIFIED
Hoja, Danielledanielle.hoja (at) dlr.deUNSPECIFIED
Buchroithner, ManfredTU DresdenUNSPECIFIED
Date:2011
Journal or Publication Title:Proceedings of the EARSeL 7th SIG-Imaging Spectroscopy Workshop
Refereed publication:No
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Page Range:pp. 1-9
Status:Published
Keywords:Spectral library, SID-SAM mixed measure, Similarity analysis, SLC-Classifier, Statistical reliability measures
Event Title:EARSeL 7th SIG-Imaging Spectroscopy Workshop
Event Location:Edinburgh, United Kingdom
Event Type:international Conference
Event Dates:11.-13. April 2011
Organizer:EARSeL
HGF - Research field:Aeronautics, Space and Transport (old)
HGF - Program:Space (old)
HGF - Program Themes:W EO - Erdbeobachtung
DLR - Research area:Space
DLR - Program:W EO - Erdbeobachtung
DLR - Research theme (Project):W - Vorhaben Prozesse der Landoberfläche (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute
German Remote Sensing Data Center > Land Surface
Deposited By: Heiden, Dr.rer.nat. Uta
Deposited On:15 Dec 2011 10:50
Last Modified:31 Jul 2019 19:33

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.