Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/166690
Share/Export:
logo share SHARE logo core CORE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
Title

3D human pose tracking priors using geodesic mixture models

AuthorsSimo-Serra, Edgar CSIC; Torras, Carme CSIC ORCID ; Moreno-Noguer, Francesc CSIC ORCID
KeywordsRiemannian manifolds
3D human pose
Human kinematics
Mixture modelling
Probabilistic priors
Issue Date2017
PublisherSpringer Nature
CitationInternational Journal of Computer Vision 122(2): 388-408 (2017)
AbstractWe present a novel approach for learning a finite mixture model on a Riemannian manifold in which Euclidean metrics are not applicable and one needs to resort to geodesic distances consistent with the manifold geometry. For this purpose, we draw inspiration on a variant of the expectation-maximization algorithm, that uses a minimum message length criterion to automatically estimate the optimal number of components from multivariate data lying on an Euclidean space. In order to use this approach on Riemannian manifolds, we propose a formulation in which each component is defined on a different tangent space, thus avoiding the problems associated with the loss of accuracy produced when linearizing the manifold with a single tangent space. Our approach can be applied to any type of manifold for which it is possible to estimate its tangent space. Additionally, we consider using shrinkage covariance estimation to improve the robustness of the method, especially when dealing with very sparsely distributed samples. We evaluate the approach on a number of situations, going from data clustering on manifolds to combining pose and kinematics of articulated bodies for 3D human pose tracking. In all cases, we demonstrate remarkable improvement compared to several chosen baselines.
URIhttp://hdl.handle.net/10261/166690
DOI10.1007/s11263-016-0941-2
Identifiersdoi: 10.1007/s11263-016-0941-2
e-issn: 1573-1405
issn: 0920-5691
Appears in Collections:(IRII) Artículos

Files in This Item:
File Description SizeFormat
accesoRestringido.pdf15,38 kBAdobe PDFThumbnail
View/Open
Show full item record
Review this work

SCOPUSTM   
Citations

17
checked on May 10, 2022

WEB OF SCIENCETM
Citations

15
checked on May 15, 2022

Page view(s)

298
checked on May 17, 2022

Download(s)

77
checked on May 17, 2022

Google ScholarTM

Check

Altmetric

Dimensions


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.