Tuning of adaptive weight depth map generation algorithms: Exploratory data analysis and design of computer experiments (DOCE)

Vista sencilla de ítem
dc.citation.journalTitleJournal Of Mathematical Imaging And Visioneng
dc.contributor.authorAcosta, Diego
dc.contributor.authorBarandiaran, Inigo
dc.contributor.authorCongote, John
dc.contributor.authorRuiz, Oscar
dc.contributor.authorHoyos, Alejandro
dc.contributor.authorGrana, Manuel
dc.contributor.departmentUniversidad EAFIT. Departamento de Ingeniería de Procesosspa
dc.contributor.researchgroupDesarrollo y Diseño de Procesosspa
dc.date.accessioned2021-04-12T19:06:19Z
dc.date.available2021-04-12T19:06:19Z
dc.date.issued2013-09-01
dc.description.abstractIn depth map generation algorithms, parameters settings to yield an accurate disparity map estimation are usually chosen empirically or based on unplanned experiments. Algorithms' performance is measured based on the distance of the algorithm results vs. the Ground Truth by Middlebury's standards. This work shows a systematic statistical approach including exploratory data analyses on over 14000 images and designs of experiments using 31 depth maps to measure the relative influence of the parameters and to fine-tune them based on the number of bad pixels. The implemented methodology improves the performance of adaptive weight based dense depth map algorithms. As a result, the algorithm improves from 16.78 to 14.48 % bad pixels using a classical exploratory data analysis of over 14000 existing images, while using designs of computer experiments with 31 runs yielded an even better performance by lowering bad pixels from 16.78 to 13 %. © 2012 Springer Science+Business Media, LLC.eng
dc.identifierhttps://eafit.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=1297
dc.identifier.doi10.1007/s10851-012-0366-7
dc.identifier.issn09249907
dc.identifier.issn15737683
dc.identifier.otherWOS;000322018300002
dc.identifier.otherSCOPUS;2-s2.0-84880922296
dc.identifier.urihttp://hdl.handle.net/10784/28236
dc.language.isoeng
dc.publisherSPRINGER
dc.relationDOI;10.1007/s10851-012-0366-7
dc.relationWOS;000322018300002
dc.relationSCOPUS;2-s2.0-84880922296
dc.relation.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-84880922296&doi=10.1007%2fs10851-012-0366-7&partnerID=40&md5=fe08ae97b3a869f8b940862c9b86f761
dc.rightshttps://v2.sherpa.ac.uk/id/publication/issn/0924-9907
dc.sourceJournal Of Mathematical Imaging And Vision
dc.subjectComputer experimenteng
dc.subjectDepth Mapeng
dc.subjectDepth-map generationeng
dc.subjectDesigns of experimentseng
dc.subjectExploratory data analysiseng
dc.subjectStatistical approacheng
dc.subjectStatistical designeng
dc.subjectStereo image processingeng
dc.subjectExperimentseng
dc.subjectImage processingeng
dc.subjectParameter estimationeng
dc.subjectPixelseng
dc.subjectAlgorithmseng
dc.titleTuning of adaptive weight depth map generation algorithms: Exploratory data analysis and design of computer experiments (DOCE)eng
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion
dc.typeinfo:eu-repo/semantics/articleeng
dc.typearticleeng
dc.typeinfo:eu-repo/semantics/publishedVersioneng
dc.typepublishedVersioneng
dc.type.localArtículospa

Archivos

Bloque original
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
s10851-012-0366-7.pdf
Tamaño:
630.31 KB
Formato:
Adobe Portable Document Format
Descripción:
Descargar

Colecciones

Artículos