Show simple item record

AuthorThiel, Christiandc.contributor.author
AuthorGiacco, Ferdinandodc.contributor.author
AuthorPugliese, Lucadc.contributor.author
AuthorScarpetta, Silviadc.contributor.author
AuthorMarinaro, Mariadc.contributor.author
Date of accession2016-03-15T11:04:21Zdc.date.accessioned
Available in OPARU since2016-03-15T11:04:21Zdc.date.available
Year of creation2010dc.date.created
AbstractClassification of multispectral remotely sensed data with textural features is investigated with a special focus on uncertainty analysis in the produced land-cover maps. Much effort has already been directed into the research of satisfactory accuracy assessment techniques in image classification, but a common approach is not yet universally adopted. We look at the relationship between hard accuracy and the uncertainty on the produced answers, introducing two measures based on maximum probability and alpha quadratic entropy. Their impact differs depending on the type of classifier. In this paper, we deal with two different classification strategies, based on support vector machines (SVMs) and Kohonen’s self-organizing maps (SOMs), both suitably modified to give soft answers. Once the multiclass probability answer vector is available for each pixel in the image, we studied the behavior of the overall classification accuracy as a function of the uncertainty associated with each vector, given a hard-labeled test set. The experimental results show that the SVM with one-versus-one architecture and linear kernel clearly outperforms the other supervised approaches in terms of overall accuracy. On the other hand, our analysis reveals that the proposed SOM-based classifier, despite its unsupervised learning procedure, is able to provide soft answers which are the best candidates for a fusion with supervised results.dc.description.abstract
Languageendc.language.iso
PublisherUniversität Ulmdc.publisher
ID of original publ.http://dx.doi.org/10.1109/TGRS.2010.2047863dc.relation.uri
LicenseStandard (ohne Print-On-Demand)dc.rights
Link to license texthttps://oparu.uni-ulm.de/xmlui/license_opod_v1dc.rights.uri
KeywordFuzzy SOMdc.subject
KeywordFuzzy SVMdc.subject
KeywordLand-cover mapsdc.subject
KeywordRemotely sensed imagesdc.subject
KeywordSoft classificationdc.subject
KeywordSOMdc.subject
KeywordSVMdc.subject
Dewey Decimal GroupDDC 004 / Data processing & computer sciencedc.subject.ddc
LCSHGeodetic satellitesdc.subject.lcsh
LCSHUncertaintydc.subject.lcsh
MeSHNeoplasms; Classificationdc.subject.mesh
TitleUncertainty analysis for the classification of multispectral satellite images using SVMs and SOMsdc.title
Resource typeWissenschaftlicher Artikeldc.type
DOIhttp://dx.doi.org/10.18725/OPARU-3899dc.identifier.doi
PPN1651371350dc.identifier.ppn
URNhttp://nbn-resolving.de/urn:nbn:de:bsz:289-vts-74122dc.identifier.urn
GNDSatellitenbilddc.subject.gnd
FacultyFakultät für Ingenieurwissenschaften und Informatikuulm.affiliationGeneral
Citation of original publ.IEEE transactions on geoscience and remote sensing 48 (2010), 10, S. 3769 - 3779uulm.citationOrigPub
Date of activation2010-11-07T23:28:52Zuulm.freischaltungVTS
Peer reviewjauulm.peerReview
DCMI TypeTextuulm.typeDCMI
VTS-ID7412uulm.vtsID
CategoryPublikationenuulm.category


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record