Exploring the Potential of Machine Learning for Automatic Slum Identification from VHR Imagery

Vista sencilla de ítem
dc.citation.journalTitleRemote Sensing
dc.contributor.authorDuque JCspa
dc.contributor.authorPatiño, Jorgespa
dc.contributor.authorBetancourt, Alejandrospa
dc.contributor.departmentUniversidad EAFIT. Departamento de Economía y Finanzasspa
dc.contributor.researchgroupResearch in Spatial Economics (RISE)eng
dc.date.accessioned2021-04-12T14:26:19Z
dc.date.available2021-04-12T14:26:19Z
dc.date.issued2017-09-01
dc.description.abstractSlum identification in urban settlements is a crucial step in the process of formulation of pro-poor policies. However, the use of conventional methods for slum detection such as field surveys can be time-consuming and costly. This paper explores the possibility of implementing a low-cost standardized method for slum detection. We use spectral, texture and structural features extracted from very high spatial resolution imagery as input data and evaluate the capability of three machine learning algorithms (Logistic Regression, Support Vector Machine and Random Forest) to classify urban areas as slum or no-slum. Using data from Buenos Aires (Argentina), Medellin (Colombia) and Recife (Brazil), we found that Support Vector Machine with radial basis kernel delivers the best performance (with F2-scores over 0.81). We also found that singularities within cities preclude the use of a unified classification model.eng
dc.identifierhttps://eafit.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=7493
dc.identifier.doi10.1002/jid.3310
dc.identifier.issn20724292
dc.identifier.otherWOS;000438347400003
dc.identifier.otherSCOPUS;2-s2.0-85028852005
dc.identifier.urihttp://hdl.handle.net/10784/28063
dc.language.isoengeng
dc.publisherMDPI AG
dc.relation.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85029393426&doi=10.3390%2frs9090895&partnerID=40&md5=aa60fc3c6f0cb2a082890f964a30c812
dc.rightshttps://v2.sherpa.ac.uk/id/publication/issn/2072-4292
dc.sourceRemote Sensing
dc.subject.keywordremote sensingeng
dc.subject.keywordslum detectioneng
dc.subject.keywordmachine learningeng
dc.titleExploring the Potential of Machine Learning for Automatic Slum Identification from VHR Imageryeng
dc.typearticleeng
dc.typeinfo:eu-repo/semantics/articleeng
dc.typeinfo:eu-repo/semantics/publishedVersioneng
dc.typepublishedVersioneng
dc.type.localArtículospa

Archivos

Bloque original
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
rs9090895.pdf
Tamaño:
7.55 MB
Formato:
Adobe Portable Document Format
Descripción:
Descargar

Colecciones

Artículos