Particle Filtering with a Soft Detection Based Near-Optimal Importance Function for Visual Tracking

Mehdi Oulad Ameziane 1, 2 Christelle Garnier 1, 2 Yves Delignon 1, 2 Emmanuel Duflos 2 François Septier 1, 2
1 Institut TELECOM/TELECOM Lille1
2 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : Particle filters are currently widely used for visual tracking. In order to improve their performance, we propose to enrich the observation model with soft detection information and to derive a near-optimal proposal to efficiently propagate particles in the state space. This information reflecting probabilities about the object location is more reliable than the usual binary output which can yield false or missed detections. Moreover, our proposal not only incorporates the observations as in previous works, but relies on a close approximation of the optimal importance function. The resulting PF achieves high tracking accuracy and has the advantage of coping with unpredictable and abrupt movements.
Document type :
Conference papers
Complete list of metadatas
https://hal-imt.archives-ouvertes.fr/hal-01198422
Contributor : François Septier <>
Submitted on : Saturday, September 12, 2015 - 3:57:34 PM
Last modification on : Thursday, October 17, 2019 - 12:35:47 PM

Identifiers

  • HAL Id : hal-01198422, version 1

Collections

INSTITUT-TELECOM | CRISTAL-SIGMA | IMT-LILLE-DOUAI | CRISTAL | UNIV-LILLE

Citation

Mehdi Oulad Ameziane, Christelle Garnier, Yves Delignon, Emmanuel Duflos, François Septier. Particle Filtering with a Soft Detection Based Near-Optimal Importance Function for Visual Tracking. 23rd European Signal Processing Conference (EUSIPCO), Aug 2015, Nice, France. ⟨hal-01198422⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

215

Contact

CCSD