Logo do repositório
 
Publicação

Land cover classification from multispectral data using computational intelligence tools

2017-11-15Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorMora, André
dc.contributor.authorSantos, Tiago M. A.
dc.contributor.authorLukasik, Szymon
dc.contributor.authorSilva, João M. N.
dc.contributor.authorFalcão, António J.
dc.contributor.authorFonseca, José M.
dc.contributor.authorRibeiro, Rita A.
dc.contributor.institutionCTS - Centro de Tecnologia e Sistemas
dc.contributor.institutionUNINOVA-Instituto de Desenvolvimento de Novas Tecnologias
dc.contributor.pblMDPI - Multidisciplinary Digital Publishing Institute
dc.date.accessioned2018-07-20T22:14:05Z
dc.date.available2018-07-20T22:14:05Z
dc.date.issued2017-11-15
dc.descriptionThis work was partially funded by FCT Strategic Program UID/EEA/00066/203 of the Center of Technologies and System (CTS) of UNINOVA-Institute for the Development of new Technologies. It is also partially based on work from COST Action TD1403 "Big Data Era in Sky and Earth Observation", supported by COST (European Cooperation in Science and Technology).
dc.description.abstractThis article discusses how computational intelligence techniques are applied to fuse spectral images into a higher level image of land cover distribution for remote sensing, specifically for satellite image classification. We compare a fuzzy-inference method with two other computational intelligence methods, decision trees and neural networks, using a case study of land cover classification from satellite images. Further, an unsupervised approach based on k-means clustering has been also taken into consideration for comparison. The fuzzy-inference method includes training the classifier with a fuzzy-fusion technique and then performing land cover classification using reinforcement aggregation operators. To assess the robustness of the four methods, a comparative study including three years of land cover maps for the district of Mandimba, Niassa province, Mozambique, was undertaken. Our results show that the fuzzy-fusion method performs similarly to decision trees, achieving reliable classifications; neural networks suffer from overfitting; while k-means clustering constitutes a promising technique to identify land cover types from unknown areas.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent7403203
dc.identifier.doi10.3390/info8040147
dc.identifier.issn2078-2489
dc.identifier.otherPURE: 3679539
dc.identifier.otherPURE UUID: 7a05f3e0-6833-4b71-a813-a5417e363ea5
dc.identifier.otherScopus: 85036460977
dc.identifier.otherWOS: 000424337100034
dc.identifier.otherORCID: /0000-0001-7173-7374/work/42961027
dc.identifier.urihttp://www.scopus.com/inward/record.url?scp=85036460977&partnerID=8YFLogxK
dc.identifier.urlhttps://www.scopus.com/pages/publications/85036460977
dc.language.isoeng
dc.peerreviewedyes
dc.subjectAggregation operators
dc.subjectImage fusion
dc.subjectLand cover classification
dc.subjectRemote sensing
dc.subjectInformation Systems
dc.titleLand cover classification from multispectral data using computational intelligence toolsen
dc.title.subtitleA comparative studyen
dc.typejournal article
degois.publication.issue4
degois.publication.titleInformation (Switzerland)
degois.publication.volume8
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
information_08_00147.pdf
Tamanho:
7.06 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (FCT)