Contour people: a paremeterized model of 2D articulated human shape (Contributo in atti di convegno)

Type
Label
  • Contour people: a paremeterized model of 2D articulated human shape (Contributo in atti di convegno) (literal)
Anno
  • 2010-01-01T00:00:00+01:00 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#doi
  • 10.1109/CVPR.2010.5540154 (literal)
Alternative label
  • O. Freifeld, A. Weiss, S. Zuffi, M. J. Black (2010)
    Contour people: a paremeterized model of 2D articulated human shape
    in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), S. Francisco (USA), 13-18 Giugno 2010
    (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
  • O. Freifeld, A. Weiss, S. Zuffi, M. J. Black (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#url
  • http://www.cs.brown.edu/~zuffi/Site/Welcome_files/freifeldCVPR10.pdf (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#titoloVolume
  • Computer Vision and Pattern Recognition (CVPR), 2010 IEEE (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#volumeInCollana
  • 1063-6919 (literal)
Note
  • Google Scholar (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
  • O. Freifeld, Division of Applied Mathematics, Brown University A. Weiss, Department of Computer Science, Brown University S. Zuffi, ITC-CNR and Department of Computer Science, Brown University M. J. Black, Department of Computer Science, Brown University (literal)
Titolo
  • Contour people: a paremeterized model of 2D articulated human shape (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#isbn
  • 978-1-4244-6984-0 (literal)
Abstract
  • We define a new \"contour person\" model of the human body that has the expressive power of a detailed 3D model and the computational benefits of a simple 2D part-based model. The contour person (CP) model is learned from a 3D SCAPE model of the human body that captures natural shape and pose variations; the projected contours of this model, along with their segmentation into parts forms the training set. The CP model factors deformations of the body into three components: shape variation, viewpoint change and part rotation. This latter model also incorporates a learned non-rigid deformation model. The result is a 2D articulated model that is compact to represent, simple to compute with and more expressive than previous models. We demonstrate the value of such a model in 2D pose es- timation and segmentation. Given an initial pose from a standard pictorial-structures method, we refine the pose and shape using an objective function that segments the scene into foreground and background regions. The result is a parametric, human-specific, image segmentation. (literal)
Prodotto di
Autore CNR

Incoming links:


Autore CNR di
Prodotto
data.CNR.it