Please use this identifier to cite or link to this item:
logo share SHARE BASE
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE

Invite to open peer review

Single image 3D human pose estimation from noisy observations

AuthorsSimo-Serra, Edgar CSIC; Ramisa, Arnau CSIC ORCID; Alenyà, Guillem CSIC ORCID ; Torras, Carme CSIC ORCID ; Moreno-Noguer, Francesc CSIC ORCID
Issue Date2012
PublisherInstitute of Electrical and Electronics Engineers
CitationIEEE Conference on Computer Vision and Pattern Recognition: 2673-2680 (2012)
AbstractMarkerless 3D human pose detection from a single image is a severely underconstrained problem because different 3D poses can have similar image projections. In order to handle this ambiguity, current approaches rely on prior shape models that can only be correctly adjusted if 2D image features are accurately detected. Unfortunately, although current 2D part detector algorithms have shown promising results, they are not yet accurate enough to guarantee a complete disambiguation of the 3D inferred shape. In this paper, we introduce a novel approach for estimating 3D human pose even when observations are noisy. We propose a stochastic sampling strategy to propagate the noise from the image plane to the shape space. This provides a set of ambiguous 3D shapes, which are virtually undistinguishable from their image projections. Disambiguation is then achieved by imposing kinematic constraints that guarantee the resulting pose resembles a 3D human shape. We validate the method on a variety of situations in which state-of-the-art 2D detectors yield either inaccurate estimations or partly miss some of the body parts.
DescriptionTrabajo presentado al CVPR celebrado en Providence (USA) del 16 al 21 de junio de 2012.
Publisher version (URL)
Identifiersdoi: 10.1109/CVPR.2012.6247988
isbn: 978-1-4673-1226-4
Appears in Collections:(IRII) Libros y partes de libros

Files in This Item:
File Description SizeFormat
Single image 3D human.pdf4,91 MBUnknownView/Open
Show full item record

CORE Recommender

Page view(s)

checked on May 18, 2024


checked on May 18, 2024

Google ScholarTM




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