Action-specific motion prior for efficient Bayesian 3D human body tracking

  • Authors:
  • Ignasi Rius;Jordi Gonzílez;Javier Varona;F. Xavier Roca

  • Affiliations:
  • Centre de Visió per Computador (CVC-UAB), Edifici O, Campus Universitat Autònoma de Barcelona, 08193 Bellaterra, Barcelona, Spain;Centre de Visió per Computador (CVC-UAB), Edifici O, Campus Universitat Autònoma de Barcelona, 08193 Bellaterra, Barcelona, Spain;Departament de Matemítiques i Informítica, Universitat de les Illes Balears (UIB), Palma de Mallorca, Spain;Centre de Visió per Computador (CVC-UAB), Edifici O, Campus Universitat Autònoma de Barcelona, 08193 Bellaterra, Barcelona, Spain

  • Venue:
  • Pattern Recognition
  • Year:
  • 2009

Quantified Score

Hi-index 0.01

Visualization

Abstract

In this paper, we aim to reconstruct the 3D motion parameters of a human body model from the known 2D positions of a reduced set of joints in the image plane. Towards this end, an action-specific motion model is trained from a database of real motion-captured performances, and used within a particle filtering framework as a priori knowledge on human motion. First, our dynamic model guides the particles according to similar situations previously learnt. Then, the state space is constrained so only feasible human postures are accepted as valid solutions at each time step. As a result, we are able to track the 3D configuration of the full human body from several cycles of walking motion sequences using only the 2D positions of a very reduced set of joints from lateral or frontal viewpoints.