Joint estimation of segmentation and structure from motion

We present a novel optimisation framework for the estimation of the multi-body motion segmentation and 3D reconstruction of a set of point trajectories in the presence of missing data. The proposed solution not only assigns the trajectories to the correct motion but it also solves for the 3D locatio...

Descripción completa

Detalles Bibliográficos
Autores: Zappella, Luca, Del Bue, Alessio, Lladó Bardera, Xavier, Salvi, Joaquim
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2013
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:recercat.cat:10256/11544
Acceso en línea:http://hdl.handle.net/10256/11544
Access Level:acceso embargado
Palabra clave:Imatges -- Processament
Image processing
Visió per ordinador
Computer vision
id ES_8bcc29d01bfe0f512bd3ccc77fcddcd9
oai_identifier_str oai:recercat.cat:10256/11544
network_acronym_str ES
network_name_str España
repository_id_str
spelling Joint estimation of segmentation and structure from motionZappella, LucaDel Bue, AlessioLladó Bardera, XavierSalvi, JoaquimImatges -- ProcessamentImage processingVisió per ordinadorComputer visionWe present a novel optimisation framework for the estimation of the multi-body motion segmentation and 3D reconstruction of a set of point trajectories in the presence of missing data. The proposed solution not only assigns the trajectories to the correct motion but it also solves for the 3D location of multi-body shape and it fills the missing entries in the measurement matrix. Such a solution is based on two fundamental principles: each of the multi-body motions is controlled by a set of metric constraints that are given by the specific camera model, and the shape matrix that describes the multi-body 3D shape is generally sparse. We jointly include such constraints in a unique optimisation framework which, starting from an initial segmentation, iteratively enforces these set of constraints in three stages. First, metric constraints are used to estimate the 3D metric shape and to fill the missing entries according to an orthographic camera model. Then, wrongly segmented trajectories are detected by using sparse optimisation of the shape matrix. A final reclassification strategy assigns the detected points to the right motion or discards them as outliers. We provide experiments that show consistent improvements to previous approaches both on synthetic and real dataThis work has been supported by the Spanish Ministry of Science and Innovation projects CTM2011-29691-C02-02. L. Zappella was supported by the Catalan government scholarship 2009FI B1 00068ElsevierMinisterio de Ciencia e Innovación (Espanya)infoinfo2013info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://hdl.handle.net/10256/11544http://hdl.handle.net/10256/11544© Computer Vision and Image Understanding, 2013, vol. 117, núm. 2, p. 113-129Articles publicats (D-ATC)reponame:Recercat. Dipósit de la Recerca de Catalunyainstname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)Inglésinfo:eu-repo/semantics/altIdentifier/doi/10.1016/j.cviu.2012.09.004info:eu-repo/semantics/altIdentifier/issn/1077-3142info:eu-repo/grantAgreement/MICINN//CTM2011-29691-C02-02Tots els drets reservatsinfo:eu-repo/semantics/embargoedAccessoai:recercat.cat:10256/115442026-05-29T05:05:01Z
dc.title.none.fl_str_mv Joint estimation of segmentation and structure from motion
title Joint estimation of segmentation and structure from motion
spellingShingle Joint estimation of segmentation and structure from motion
Zappella, Luca
Imatges -- Processament
Image processing
Visió per ordinador
Computer vision
title_short Joint estimation of segmentation and structure from motion
title_full Joint estimation of segmentation and structure from motion
title_fullStr Joint estimation of segmentation and structure from motion
title_full_unstemmed Joint estimation of segmentation and structure from motion
title_sort Joint estimation of segmentation and structure from motion
dc.creator.none.fl_str_mv Zappella, Luca
Del Bue, Alessio
Lladó Bardera, Xavier
Salvi, Joaquim
author Zappella, Luca
author_facet Zappella, Luca
Del Bue, Alessio
Lladó Bardera, Xavier
Salvi, Joaquim
author_role author
author2 Del Bue, Alessio
Lladó Bardera, Xavier
Salvi, Joaquim
author2_role author
author
author
dc.contributor.none.fl_str_mv Ministerio de Ciencia e Innovación (Espanya)
dc.subject.none.fl_str_mv Imatges -- Processament
Image processing
Visió per ordinador
Computer vision
topic Imatges -- Processament
Image processing
Visió per ordinador
Computer vision
description We present a novel optimisation framework for the estimation of the multi-body motion segmentation and 3D reconstruction of a set of point trajectories in the presence of missing data. The proposed solution not only assigns the trajectories to the correct motion but it also solves for the 3D location of multi-body shape and it fills the missing entries in the measurement matrix. Such a solution is based on two fundamental principles: each of the multi-body motions is controlled by a set of metric constraints that are given by the specific camera model, and the shape matrix that describes the multi-body 3D shape is generally sparse. We jointly include such constraints in a unique optimisation framework which, starting from an initial segmentation, iteratively enforces these set of constraints in three stages. First, metric constraints are used to estimate the 3D metric shape and to fill the missing entries according to an orthographic camera model. Then, wrongly segmented trajectories are detected by using sparse optimisation of the shape matrix. A final reclassification strategy assigns the detected points to the right motion or discards them as outliers. We provide experiments that show consistent improvements to previous approaches both on synthetic and real data
publishDate 2013
dc.date.none.fl_str_mv 2013
info
info
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10256/11544
http://hdl.handle.net/10256/11544
url http://hdl.handle.net/10256/11544
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1016/j.cviu.2012.09.004
info:eu-repo/semantics/altIdentifier/issn/1077-3142
info:eu-repo/grantAgreement/MICINN//CTM2011-29691-C02-02
dc.rights.none.fl_str_mv Tots els drets reservats
info:eu-repo/semantics/embargoedAccess
rights_invalid_str_mv Tots els drets reservats
eu_rights_str_mv embargoedAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv © Computer Vision and Image Understanding, 2013, vol. 117, núm. 2, p. 113-129
Articles publicats (D-ATC)
reponame:Recercat. Dipósit de la Recerca de Catalunya
instname:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
instname_str Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
reponame_str Recercat. Dipósit de la Recerca de Catalunya
collection Recercat. Dipósit de la Recerca de Catalunya
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869412851961036800
score 15.81155