Exploiting spatio-temporal constraints for robust 2D pose tracking

Gregory Rogez, Ignasi Rius, Jesus Martinez-del-Rincon, Carlos Orrite

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)


We present a Spatio-temporal 2D Models Framework (STMF) for 2D-Pose tracking. Space and time are discretized and a mixture of probabilistic "local models" is learnt associating 2D Shapes and 2D Stick Figures. Those spatio-temporal models generalize well for a particular viewpoint and state of the tracked action but some spatio-temporal discontinuities can appear along a sequence, as a direct consequence of the discretization. To overcome the problem, we propose to apply a Rao-Blackwellized Particle Filter (RBPF) in the 2D-Pose eigenspace, thus interpolating unseen data between view-based clusters. The fitness to the images of the predicted 2D-Poses is evaluated combining our STMF with spatio-temporal constraints. A robust, fast and smooth human motion tracker is obtained by tracking only the few most important dimensions of the state space and by refining deterministically with our STMF.

Original languageEnglish
Title of host publicationHuman Motion - Understanding, Modeling, Capture and Animation, Proceedings
EditorsA Elgammal, B Rosenhahn, R Klette
Place of PublicationBERLIN
Number of pages16
Volume4814 LNCS
ISBN (Print)978-3-540-75702-3
Publication statusPublished - 2007
Event2nd Workshop on Human Motion Understanding, Modeling, Capture and Animation - Rio de Janeiro, Brazil
Duration: 20 Oct 2007 → …


Conference2nd Workshop on Human Motion Understanding, Modeling, Capture and Animation
CityRio de Janeiro
Period20/10/2007 → …

ASJC Scopus subject areas

  • General Biochemistry,Genetics and Molecular Biology
  • General Computer Science
  • Theoretical Computer Science


Dive into the research topics of 'Exploiting spatio-temporal constraints for robust 2D pose tracking'. Together they form a unique fingerprint.

Cite this