Real Time Parallel Implementation of a Particle Filter Based Visual Tracking

  title={Real Time Parallel Implementation of a Particle Filter Based Visual Tracking},
  author={Joel Falcou and Thierry Chateau and Jocelyn S{\'e}rot and Jean-Thierry Laprest{\'e}},
Particle filtering is a widely used method to solve vision tracking problems. However, to be able to run in real-time on standard architecture, the state vector used in the particle filter must remain small [1]. We propose a parallel implementation of a 3D tracking algorithm operating on a stereo video stream and running in real-time on a cluster architecture. We demonstrate the efficiency of this implementation with a pedestrian tracking application. 

From This Paper

Figures, tables, results, connections, and topics extracted from this paper.
4 Extracted Citations
12 Extracted References
Similar Papers

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 12 references

Serot: E.V.E., An Object Oriented SIMD Library

  • J. J. Falcou
  • Scalable Computing: Practice and Experience
  • 2005
1 Excerpt

A tutorial on particle filters for on-line non-linear/non-gaussian bayesian tracking

  • S. Arulampalam, S. Maskell, N. Gordon, T. Clapp
  • IEEE Transactions on Signal Processing 50
  • 2002
1 Excerpt

Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods

  • J. Platt
  • Advances in Large Margin Classifiers
  • 1999

Similar Papers

Loading similar papers…