Mostrar el registro sencillo del ítem

dc.contributor.authorJaimez, Mariano
dc.contributor.authorSouiai, Mohamed
dc.contributor.authorStuckler, Jorg
dc.contributor.authorGonzalez-Jimenez, Javier
dc.contributor.authorCremers, Daniel
dc.date.accessioned2016-01-07T10:29:39Z
dc.date.available2016-01-07T10:29:39Z
dc.date.created2015
dc.date.issued2016-01-07
dc.identifier.urihttp://hdl.handle.net/10630/10863
dc.description.abstractWe propose a novel joint registration and segmentation approach to estimate scene flow from RGB-D images. Instead of assuming the scene to be composed of a number of independent rigidly-moving parts, we use non-binary labels to capture non-rigid deformations at transitions between the rigid parts of the scene. Thus, the velocity of any point can be computed as a linear combination (interpolation) of the estimated rigid motions, which provides better results than traditional sharp piecewise segmentations. Within a variational framework, the smooth segments of the scene and their corresponding rigid velocities are alternately refined until convergence. A K-means-based segmentation is employed as an initialization, and the number of regions is subsequently adapted during the optimization process to capture any arbitrary number of independently moving objects. We evaluate our approach with both synthetic and real RGB-D images that contain varied and large motions. The experiments show that our method estimates the scene flow more accurately than the most recent works in the field, and at the same time provides a meaningful segmentation of the scene based on 3D motion.es_ES
dc.description.sponsorshipUniversidad de Málaga. Campus de Excelencia Internacional Andalucía Tech. Spanish Government under the grant programs FPI-MICINN 2012 and DPI2014- 55826-R (co-founded by the European Regional Development Fund), as well as by the EU ERC grant Convex Vision (grant agreement no. 240168).es_ES
dc.language.isoenges_ES
dc.rightsinfo:eu-repo/semantics/openAccesses_ES
dc.subjectVisión por ordenadores_ES
dc.subject.otherRGB-D cameraes_ES
dc.subject.otherComputer visiones_ES
dc.subject.otherVariational methodses_ES
dc.subject.otherScene flowes_ES
dc.titleMotion Cooperation: Smooth Piece-Wise Rigid Scene Flow from RGB-D Imageses_ES
dc.typeinfo:eu-repo/semantics/workingPaperes_ES
dc.centroE.T.S.I. Informáticaes_ES
dc.relation.eventtitleInternational Conference on 3D Visiones_ES
dc.relation.eventplaceLyon, Francees_ES
dc.relation.eventdate19-22 Octoberes_ES
dc.identifier.orcidhttp://orcid.org/0000-0003-3845-3497es_ES
dc.cclicenseby-nc-ndes_ES


Ficheros en el ítem

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem