English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/133132
Share/Impact:
Statistics
logo share SHARE   Add this article to your Mendeley library MendeleyBASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL
Exportar a otros formatos:
Title

Lie algebra-based kinematic prior for 3D human pose tracking

AuthorsSimo-Serra, Edgar ; Torras, Carme ; Moreno-Noguer, Francesc
Issue Date2015
CitationIAPR International Conference on Machine Vision Applications (2015)
AbstractWe propose a novel kinematic prior for 3D human pose tracking that allows predicting the position in subsequent frames given the current position. We first define a Riemannian manifold that models the pose and extend it with its Lie algebra to also be able to represent the kinematics. We then learn a joint Gaussian mixture model of both the human pose and the kinematics on this manifold. Finally by conditioning the kinematics on the pose we are able to obtain a distribution of poses for subsequent frames that which can be used as a reliable prior in 3D human pose tracking. Our model scales well to large amounts of data and can be sampled at over 100,000 samples/second. We show it outperforms the widely used Gaussian diffusion model on the challenging Human3.6M dataset.
DescriptionTrabajo presentado a la IAPR International Conference on Machine Vision Applications (MVA) celebrada en Tokyo (Japón) del 18 al 22 de mayo de 2015.
URIhttp://hdl.handle.net/10261/133132
Appears in Collections:(IRII) Comunicaciones congresos
Files in This Item:
File Description SizeFormat 
posetracking.pdf243,7 kBAdobe PDFThumbnail
View/Open
Show full item record
Review this work
 


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