Statistical tuning of adaptive-weight depth map algorithm

dc.contributor.authorHoyos, Alejandro
dc.contributor.authorCongote, John
dc.contributor.authorBarandiaran, Inigo
dc.contributor.authorAcosta, Diego
dc.contributor.authorRuiz, Oscar
dc.contributor.departmentUniversidad EAFIT. Departamento de Ingeniería de Procesosspa
dc.contributor.researchgroupDesarrollo y Diseño de Procesosspa
dc.date.accessioned2021-04-12T19:08:53Z
dc.date.available2021-04-12T19:08:53Z
dc.date.issued2011-01-01
dc.description.abstractIn depth map generation, the settings of the algorithm parameters to yield an accurate disparity estimation are usually chosen empirically or based on unplanned experiments. A systematic statistical approach including classical and exploratory data analyses on over 14000 images to measure the relative influence of the parameters allows their tuning based on the number of bad-pixels. Our approach is systematic in the sense that the heuristics used for parameter tuning are supported by formal statistical methods. The implemented methodology improves the performance of dense depth map algorithms. As a result of the statistical based tuning, the algorithm improves from 16.78% to 14.48% bad-pixels rising 7 spots as per the Middlebury Stereo Evaluation Ranking Table. The performance is measured based on the distance of the algorithm results vs. the Ground Truth by Middlebury. Future work aims to achieve the tuning by using significantly smaller data sets on fractional factorial and surface-response designs of experiments. © 2011 Springer-Verlag.eng
dc.identifierhttps://eafit.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=1593
dc.identifier.doi10.1007/978-3-642-23678-5_67
dc.identifier.issn03029743
dc.identifier.issn16113349
dc.identifier.otherWOS;000300567300067
dc.identifier.otherSCOPUS;2-s2.0-80052785311
dc.identifier.urihttp://hdl.handle.net/10784/28292
dc.language.isoeng
dc.publisherSPRINGER
dc.relationDOI;10.1007/978-3-642-23678-5_67
dc.relationWOS;000300567300067
dc.relationSCOPUS;2-s2.0-80052785311
dc.relation.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-80052785311&doi=10.1007%2f978-3-642-23678-5_67&partnerID=40&md5=bb2b4a2df550bee4837162d32849c7a7
dc.rightshttps://v2.sherpa.ac.uk/id/publication/issn/0302-9743
dc.sourceLecture Notes In Computer Science
dc.subject.keywordAlgorithm parameterseng
dc.subject.keywordData setseng
dc.subject.keywordDense depth mapeng
dc.subject.keywordDepth Mapeng
dc.subject.keywordDepth-map generationeng
dc.subject.keywordDesigns of experimentseng
dc.subject.keywordDisparity estimationseng
dc.subject.keywordExploratory data analysiseng
dc.subject.keywordFractional factorialseng
dc.subject.keywordGround trutheng
dc.subject.keywordParameter-tuningeng
dc.subject.keywordRanking tableseng
dc.subject.keywordStatistical approacheng
dc.subject.keywordStereo image processingeng
dc.subject.keywordData reductioneng
dc.subject.keywordExperimentseng
dc.subject.keywordImage analysiseng
dc.subject.keywordParameter estimationeng
dc.subject.keywordPixelseng
dc.subject.keywordAlgorithmseng
dc.titleStatistical tuning of adaptive-weight depth map algorithmeng
dc.typeinfo:eu-repo/semantics/conferencePapereng
dc.typeconferencePapereng
dc.typeinfo:eu-repo/semantics/publishedVersioneng
dc.typepublishedVersioneng
dc.type.localDocumento de conferenciaspa

Archivos