Publicação

Slum mapping : a comparison of single class learning and expert system object-oriented classification for mapping slum settlements in Addis Ababa city, Ethiopia

Ver documento

Detalhes bibliográficos
Resumo:Updated spatial information on the dynamics of slums can be helpful to measure and evaluate the progress of urban upgrading projects and policies. Earlier studies have shown that remote sensing techniques, with the help of very-high resolution imagery, can play a significant role in detecting slums, and providing timely spatial information. The main objective of this thesis is to develop a reliable object-oriented slum identification technique that enables the provision of timely spatial information about slum settlements in Addis Ababa city. It compares the one-class support vector machines algorithm with the expert defined classification rule set in the discrimination of slums, using GeoEye-1 imagery. Two different approaches, called manual and automatic fine-tuning, were deployed to determine the best value of parameters in one-class support vector machines algorithm. The manual fine-tuning of the parameters is done using extensive manual trial. The automatic tuning is done using cross-validation grid search with the overall accuracy as the performance metric. Two regions of study were defined with different landscape compositions, providing different classification scenarios to compare the classification approaches. After image segmentation, twenty predictive variables were computed to characterize the objects in both study areas. An image analyst collected one hundred sample objects of a slum to be used as training for the single-class learner. In parallel, an image analyst has defined a hierarchical rule set to discriminate the class of interest. Results in both study areas indicate that the one-class support vector machine with manual tuning yields higher overall accuracy (97.7% in subset 1, and 92% in subset 2) and requiring much less application effort and computing time than the expert system.
Autores principais:Tesfay, Mulu Weldegebreal
Assunto:Remote sensing Image segmentation Image classification Object-oriented image analysis Single class learning One class support vector machine Expert system classification
Ano:2018
País:Portugal
Tipo de documento:dissertação de mestrado
Tipo de acesso:acesso aberto
Instituição associada:Universidade Nova de Lisboa
Idioma:inglês
Origem:Repositório Institucional da UNL
_version_ 1868983326849630208
author Tesfay, Mulu Weldegebreal
author_facet Tesfay, Mulu Weldegebreal
author_role author
contributor_name_str_mv Silva, Joel Dinis Baptista Ferreira da
Caetano, Mário Sílvio Rochinha de Andrade
Guerrero, Ignacio
RUN
country_str PT
creators_json_txt [{\"Person.name\":\"Tesfay, Mulu Weldegebreal\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Silva, Joel Dinis Baptista Ferreira da
Caetano, Mário Sílvio Rochinha de Andrade
Guerrero, Ignacio
RUN
datacite.creators.creator.creatorName.fl_str_mv Tesfay, Mulu Weldegebreal
datacite.date.Accepted.fl_str_mv 2018-02-27T00:00:00Z
datacite.date.available.fl_str_mv 2018-04-03T14:50:33Z
datacite.date.embargoed.fl_str_mv 2018-04-03T14:50:33Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Remote sensing
Image segmentation
Image classification
Object-oriented image analysis
Single class learning
One class support vector machine
Expert system classification
datacite.titles.title.fl_str_mv Slum mapping : a comparison of single class learning and expert system object-oriented classification for mapping slum settlements in Addis Ababa city, Ethiopia
dc.contributor.none.fl_str_mv Silva, Joel Dinis Baptista Ferreira da
Caetano, Mário Sílvio Rochinha de Andrade
Guerrero, Ignacio
RUN
dc.creator.none.fl_str_mv Tesfay, Mulu Weldegebreal
dc.date.Accepted.fl_str_mv 2018-02-27T00:00:00Z
dc.date.available.fl_str_mv 2018-04-03T14:50:33Z
dc.date.embargoed.fl_str_mv 2018-04-03T14:50:33Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10362/33711
dc.language.none.fl_str_mv eng
dc.rights.cclincense.fl_str_mv http://creativecommons.org/licenses/by/4.0/
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv Remote sensing
Image segmentation
Image classification
Object-oriented image analysis
Single class learning
One class support vector machine
Expert system classification
dc.title.fl_str_mv Slum mapping : a comparison of single class learning and expert system object-oriented classification for mapping slum settlements in Addis Ababa city, Ethiopia
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_bdcc
description Updated spatial information on the dynamics of slums can be helpful to measure and evaluate the progress of urban upgrading projects and policies. Earlier studies have shown that remote sensing techniques, with the help of very-high resolution imagery, can play a significant role in detecting slums, and providing timely spatial information. The main objective of this thesis is to develop a reliable object-oriented slum identification technique that enables the provision of timely spatial information about slum settlements in Addis Ababa city. It compares the one-class support vector machines algorithm with the expert defined classification rule set in the discrimination of slums, using GeoEye-1 imagery. Two different approaches, called manual and automatic fine-tuning, were deployed to determine the best value of parameters in one-class support vector machines algorithm. The manual fine-tuning of the parameters is done using extensive manual trial. The automatic tuning is done using cross-validation grid search with the overall accuracy as the performance metric. Two regions of study were defined with different landscape compositions, providing different classification scenarios to compare the classification approaches. After image segmentation, twenty predictive variables were computed to characterize the objects in both study areas. An image analyst collected one hundred sample objects of a slum to be used as training for the single-class learner. In parallel, an image analyst has defined a hierarchical rule set to discriminate the class of interest. Results in both study areas indicate that the one-class support vector machine with manual tuning yields higher overall accuracy (97.7% in subset 1, and 92% in subset 2) and requiring much less application effort and computing time than the expert system.
dirty 0
eu_rights_str_mv openAccess
format masterThesis
fulltext.url.fl_str_mv https://run.unl.pt/bitstreams/ea0d590b-c751-4cc7-addf-70b89612a692/download
id run_3dc054e6cd86f2fec5b7aaf5a9474cbc
identifier.url.fl_str_mv http://hdl.handle.net/10362/33711
inst_facet_str urn:organizationAcronym:unl{{{_:::_}}}Universidade Nova de Lisboa
instacron_str unl
institution Universidade Nova de Lisboa
instname_str Universidade Nova de Lisboa
language eng
network_acronym_str run
network_name_str Repositório Institucional da UNL
oai_identifier_str oai:run.unl.pt:10362/33711
organization_str_mv urn:organizationAcronym:unl
person_str_mv Tesfay, Mulu Weldegebreal
publishDate 2018
repo_facet_str urn:repositoryAcronym:run{{{_:::_}}}Repositório Institucional da UNL
reponame_str Repositório Institucional da UNL
repository_id_str urn:repositoryAcronym:run
service_str_mv urn:repositoryAcronym:run
spelling engpt_PTUpdated spatial information on the dynamics of slums can be helpful to measure and evaluate the progress of urban upgrading projects and policies. Earlier studies have shown that remote sensing techniques, with the help of very-high resolution imagery, can play a significant role in detecting slums, and providing timely spatial information. The main objective of this thesis is to develop a reliable object-oriented slum identification technique that enables the provision of timely spatial information about slum settlements in Addis Ababa city. It compares the one-class support vector machines algorithm with the expert defined classification rule set in the discrimination of slums, using GeoEye-1 imagery. Two different approaches, called manual and automatic fine-tuning, were deployed to determine the best value of parameters in one-class support vector machines algorithm. The manual fine-tuning of the parameters is done using extensive manual trial. The automatic tuning is done using cross-validation grid search with the overall accuracy as the performance metric. Two regions of study were defined with different landscape compositions, providing different classification scenarios to compare the classification approaches. After image segmentation, twenty predictive variables were computed to characterize the objects in both study areas. An image analyst collected one hundred sample objects of a slum to be used as training for the single-class learner. In parallel, an image analyst has defined a hierarchical rule set to discriminate the class of interest. Results in both study areas indicate that the one-class support vector machine with manual tuning yields higher overall accuracy (97.7% in subset 1, and 92% in subset 2) and requiring much less application effort and computing time than the expert system.application/pdfpt_PTSlum mapping : a comparison of single class learning and expert system object-oriented classification for mapping slum settlements in Addis Ababa city, EthiopiaTesfay, Mulu WeldegebrealSilva, Joel Dinis Baptista Ferreira daCaetano, Mário Sílvio Rochinha de AndradeGuerrero, IgnacioHostingInstitutionOrganizationalRUNe-mailmailto:run@unl.ptrun@unl.ptURNurn:tid:2018925022018-04-03T14:50:33Z2018-02-272018-02-27T00:00:00ZHandlehttp://hdl.handle.net/10362/33711http://purl.org/coar/access_right/c_abf2open accessRemote sensingImage segmentationImage classificationObject-oriented image analysisSingle class learningOne class support vector machineExpert system classification3048403 bytesliteraturehttp://purl.org/coar/resource_type/c_bdccmaster thesis2018-02-27http://creativecommons.org/licenses/by/4.0/http://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://run.unl.pt/bitstreams/ea0d590b-c751-4cc7-addf-70b89612a692/download
spellingShingle Slum mapping : a comparison of single class learning and expert system object-oriented classification for mapping slum settlements in Addis Ababa city, Ethiopia
Tesfay, Mulu Weldegebreal
Remote sensing
Image segmentation
Image classification
Object-oriented image analysis
Single class learning
One class support vector machine
Expert system classification
status SINGLETON
subject.fl_str_mv Remote sensing
Image segmentation
Image classification
Object-oriented image analysis
Single class learning
One class support vector machine
Expert system classification
title Slum mapping : a comparison of single class learning and expert system object-oriented classification for mapping slum settlements in Addis Ababa city, Ethiopia
title_full Slum mapping : a comparison of single class learning and expert system object-oriented classification for mapping slum settlements in Addis Ababa city, Ethiopia
title_fullStr Slum mapping : a comparison of single class learning and expert system object-oriented classification for mapping slum settlements in Addis Ababa city, Ethiopia
title_full_unstemmed Slum mapping : a comparison of single class learning and expert system object-oriented classification for mapping slum settlements in Addis Ababa city, Ethiopia
title_short Slum mapping : a comparison of single class learning and expert system object-oriented classification for mapping slum settlements in Addis Ababa city, Ethiopia
title_sort Slum mapping : a comparison of single class learning and expert system object-oriented classification for mapping slum settlements in Addis Ababa city, Ethiopia
topic Remote sensing
Image segmentation
Image classification
Object-oriented image analysis
Single class learning
One class support vector machine
Expert system classification
topic_facet Remote sensing
Image segmentation
Image classification
Object-oriented image analysis
Single class learning
One class support vector machine
Expert system classification
url http://hdl.handle.net/10362/33711
visible 1