Real Time Parallel Implementation of a Particle Filter Based Visual Tracking

We describe the implementation of a 3D visual tracking al- gorithm on a cluster architecture.Parallelisation of the algorithm makes it possible to obtain real-time execution (more than 20 FPS) even with large state vectors, which has been proven difficult on sequential architecture. Thanks to a user-friendly software development environment, this large gain in performance is not obtained at the price of programmability.

[1]  Frank Eliassen,et al.  Techniques for Parallel Execution of the Particle Filter , 2003, SCIA.

[2]  Dinesh Manocha,et al.  Cache-efficient numerical algorithms using graphics hardware , 2007, Parallel Comput..

[3]  Thierry Chateau,et al.  A Parallel Implementation of a 3D Reconstruction Algorithm for Real-Time Vision , 2005, PARCO.

[4]  Murray Cole,et al.  Algorithmic Skeletons: Structured Management of Parallel Computation , 1989 .

[5]  Paul A. Viola,et al.  Boosting Image Retrieval , 2004, International Journal of Computer Vision.

[6]  Joel Falcou,et al.  An object oriented SIMD library. , 2005 .

[7]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[8]  Rich Caruana,et al.  Obtaining Calibrated Probabilities from Boosting , 2005, UAI.

[9]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[10]  Paul A. Viola,et al.  Detecting Pedestrians Using Patterns of Motion and Appearance , 2005, International Journal of Computer Vision.

[11]  Joel Falcou,et al.  E.V.E., An Object Oriented SIMD Library , 2005, Scalable Comput. Pract. Exp..

[12]  Tomaso A. Poggio,et al.  A general framework for object detection , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[13]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[14]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..