Recover human pose from monocular image under weak perspective projection

  • Authors:
  • Minglei Tong;Yuncai Liu;Thomas S. Huang

  • Affiliations:
  • Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University, P.R. China;Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University, P.R. China;Beckman institue, University of Illinois at Urbana-Champaign, Urbana, IL

  • Venue:
  • ICCV'05 Proceedings of the 2005 international conference on Computer Vision in Human-Computer Interaction
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we construct a novel human body model using convolution surface with articulated kinematic skeleton. The human body's pose and shape in a monocular image can be estimated from convolution curve through nonlinear optimization. The contribution of the paper is in three folds: Firstly, human model based convolution surface with articulated skeletons is presented and its shape is deformable when changing polynomial parameters and radius parameters. Secondly, we give convolution surface and curve correspondence theorem under weak perspective projection, which provide a bridge between the 3D pose and 2D contour. Thirdly, we model the human body's silhouette with convolution curve in order to estimate joint's parameters from monocular images. Evalution of the method is performed on a sequence of video frames about a walking man.