Tracking people on a Torus

Ahmed Elgammal, Chan Su Lee

Research output: Contribution to journalArticlepeer-review

72 Scopus citations

Abstract

We present a framework for monocular 3D kinematic pose tracking and viewpoint estimation of periodic and quasi-periodic human motions from an uncalibrated camera. The approach we introduce here is based on learning both the visual observation manifold and the kinematic manifold of the motion using a joint representation. We show that the visual manifold of the observed shape of a human performing a periodic motion, observed from different viewpoints, is topologically equivalent to {\em a torus manifold}. The approach we introduce here is based on {\em supervised} learning of both the visual and kinematic manifolds. Instead of learning an embedding of the manifold, we learn the geometric deformation between an ideal manifold (conceptual equivalent topological structure) and a twisted version of the manifold (the data). Experimental results show accurate estimation of the 3D body posture and the viewpoint from a single uncalibrated camera.

Original languageEnglish (US)
Pages (from-to)520-538
Number of pages19
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume31
Issue number3
DOIs
StatePublished - 2009

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Keywords

  • Human motion analysis
  • Manifold learning
  • Periodic motion
  • Supervised manifold learning
  • Tracking

Fingerprint

Dive into the research topics of 'Tracking people on a Torus'. Together they form a unique fingerprint.

Cite this