Action Recognition from Arbitrary Views using 3D Exemplars - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2007

Action Recognition from Arbitrary Views using 3D Exemplars


In this paper, we address the problem of learning compact, view-independent, realistic 3D models of human actions recorded with multiple cameras, for the purpose of recognizing those same actions from a single or few cameras, without prior knowledge about the relative orientations between the cameras and the subjects. To this aim, we propose a new framework where we model actions using three dimensional occupancy grids, built from multiple viewpoints, in an exemplar-based HMM. The novelty is, that a 3D reconstruction is not required during the recognition phase, instead learned 3D exemplars are used to produce 2D image information that is compared to the observations. Parameters that describe image projections are added as latent variables in the recognition process. In addition, the temporal Markov dependency applied to view parameters allows them to evolve during recognition as with a smoothly moving camera. The effectiveness of the framework is demonstrated with experiments on real datasets and with challenging recognition scenarios.


Fichier principal
Vignette du fichier
WBR07.pdf (678.19 Ko) Télécharger le fichier
Vignette du fichier
WBR07.png (120.55 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

inria-00544741 , version 1 (14-12-2010)



Daniel Weinland, Edmond Boyer, Rémi Ronfard. Action Recognition from Arbitrary Views using 3D Exemplars. ICCV 2007 - 11th IEEE International Conference on Computer Vision, Oct 2007, Rio de Janeiro, Brazil. pp.1-7, ⟨10.1109/ICCV.2007.4408849⟩. ⟨inria-00544741⟩
501 View
730 Download



Gmail Facebook X LinkedIn More