Motion History Volumes for Free Viewpoint Action Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2005

Motion History Volumes for Free Viewpoint Action Recognition

Abstract

Action recognition is an important and challenging topic in computer vision, with many important applications including video surveillance, automated cinematography and understanding of social interaction. Yet, most current work in gesture or action interpretation remains rooted in viewdependent representations. This paper introduces Motion History Volumes (MHV) as a free-viewpoint representation for human actions in the case of multiple calibrated, and background-subtracted, video cameras. We present algorithms for computing, aligning and comparing MHVs of different actions performed by different people in a variety of viewpoints. Alignment and comparisons are performed efficiently using Fourier transforms in cylindrical coordinates around the vertical axis. Preliminary results indicate that this representation can be used to learn and recognize basic human action classes, independently of gender, body size and viewpoint.
Fichier principal
Vignette du fichier
wrb05.pdf (726.99 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00590197 , version 1 (03-05-2011)

Identifiers

  • HAL Id : inria-00590197 , version 1

Cite

Daniel Weinland, Rémi Ronfard, Edmond Boyer. Motion History Volumes for Free Viewpoint Action Recognition. Workshop on modeling People and Human Interaction (PHI'05), Oct 2005, Beijing, China. ⟨inria-00590197⟩
420 View
311 Download

Share

Gmail Facebook X LinkedIn More