Skip navigation
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAljumaily, Harith-
dc.contributor.authorLaefer, Debra F.-
dc.contributor.authorCuadra, Dolores-
dc.identifier.citationAljumaily, H., Laefer, D., and Cuadra, D. (2017). Urban Point Cloud Mining Based on Density Clustering and MapReduce. Journal of Computing in Civil Engineering, 31(5), doi: 10.1061/(ASCE)CP.1943-5487.0000674en
dc.description.abstractThis paper proposes an approach to classify, localize, and extract automatically urban objects such as buildings and the ground surface from a digital surface model created from aerial laser scanning data. To achieve that, the approach involves three steps: 1) dividing the original data into smaller, more manageable pieces using a method based on MapReduce gridding for subspace partitioning; 2) applying the DBSCAN algorithm to identify interesting subspaces depending on point density; and 3) grouping of identified subspace to form potential objects. Validation of the method was achieved using an architecturally dense and complex portion of Dublin, Ireland. The best results were achieved with a 1 m3 sized clustering cube, for which the number of classified clusters equaled that which was derived manually and that amongst those there the following scores: correctness = 84.91%, completeness = 84.39%, and quality = 84.65%.en
dc.description.sponsorshipThis work was in part supported with funds from the European Research Council Project 307836.en
dc.subjectBuilding Extractionen
dc.subjectBig Dataen
dc.subjectDBSCAN algorithmen
dc.subjectClustering Classification approachesen
dc.titleUrban Point Cloud Mining Based on Density Clustering and MapReduceen
prism.publicationNameJournal of Computing in Civil Engineeringen
Appears in Collections:Debra Laefer's Collection

Files in This Item:
File Description SizeFormat 
dbscan v25-(JCCE).pdfFinal Draft1.65 MBAdobe PDFView/Open

Items in FDA are protected by copyright, with all rights reserved, unless otherwise indicated.