Statistical tuning of Adaptive-Weight Depth Map Algorithm

Vista sencilla de ítem
dc.contributor.authorHoyos, Alejandro
dc.contributor.authorCongote, John
dc.contributor.authorBarandiaran, Iñigo
dc.contributor.authorAcosta, Diego
dc.contributor.authorRuíz, Óscar
dc.contributor.departmentUniversidad EAFIT. Departamento de Ingeniería Mecánicaspa
dc.contributor.researchgroupLaboratorio CAD/CAM/CAEspa
dc.date.accessioned2016-11-18T22:54:00Z
dc.date.available2016-11-18T22:54:00Z
dc.date.issued2011
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 signicantly smaller data sets on fractional factorial and surface-response designs of experimentseng
dc.description.note563-572spa
dc.formatapplication/pdfeng
dc.identifier.citation@incollection{acosta_springer_2011 year={2011}, isbn={978-3-642-23677-8}, booktitle={Computer Analysis of Images and Patterns}, volume={6855}, series={Lecture Notes in Computer Science}, editor={Real, Pedro and Diaz-Pernil, Daniel and Molina-Abril, Helena and Berciano, Ainhoa and Kropatsch, Walter}, doi={10.1007/978-3-642-23678-5_67}, title={Statistical Tuning of Adaptive-Weight Depth Map Algorithm}, url={http://dx.doi.org/10.1007/978-3-642-23678-5_67}, publisher={Springer Berlin Heidelberg}, keywords={Stereo Image Processing; Parameter Estimation; Depth Map}, author={Hoyos, Alejandro and Congote, John and Barandiaran, Iñigo and Acosta, Diego and Ruiz, Oscar}, pages={563-572}, language={English} }spa
dc.identifier.doi10.1007/978-3-642-23678-5_67
dc.identifier.urihttp://hdl.handle.net/10784/9726
dc.language.isoengspa
dc.publisherSpringer Berlin Heidelberg
dc.relation.ispartofComputer Analysis of Images and Patternsspa
dc.relation.isversionofhttp://www.dx.doi.org/10.1007/978-3-642-23678-5_67spa
dc.rights.accessrightsinfo:eu-repo/semantics/closedAccesseng
dc.rights.localAcceso cerradospa
dc.subject.keywordHeuristic programmingeng
dc.subject.keywordImage processingeng
dc.subject.keywordMultivariate analysiseng
dc.subject.keywordRegression analysiseng
dc.subject.keywordParameter estimationeng
dc.subject.keywordFactorial experiments designseng
dc.subject.keywordReconstrucción de la profundidadspa
dc.subject.keywordMapas de profundidadspa
dc.subject.keywordDistancia Euclidianaspa
dc.subject.keywordVisión estéreospa
dc.subject.lembPROGRAMACIÓN HEURÍSTICAspa
dc.subject.lembPROCESAMIENTO DE IMÁGENESspa
dc.subject.lembANÁLISIS MULTIVARIANTEspa
dc.subject.lembANÁLISIS DE REGRESIÓNspa
dc.subject.lembESTIMACIÓN DE PARÁMETROSspa
dc.subject.lembDISEÑO EXPERIMENTAL DE FACTORESspa
dc.titleStatistical tuning of Adaptive-Weight Depth Map Algorithmeng
dc.typeinfo:eu-repo/semantics/bookParteng
dc.typebookParteng
dc.typeinfo:eu-repo/semantics/publishedVersioneng
dc.typepublishedVersioneng
dc.type.hasVersionObra publicadaspa
dc.type.localCapítulo o parte de un librospa

Archivos

Bloque original
Mostrando 1 - 2 de 2
No hay miniatura disponible
Nombre:
statistical_tuning_depth_algorithm.pdf
Tamaño:
1.49 MB
Formato:
Adobe Portable Document Format
Descripción:
Versión incompleta
Descargar
No hay miniatura disponible
Nombre:
table_of_contents_computer_analysis_images_patterns.pdf
Tamaño:
179.93 KB
Formato:
Adobe Portable Document Format
Descripción:
Tabla de contenidos
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
2.5 KB
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar

Colecciones

Capítulos en libros