Skip to Main content Skip to Navigation
Conference papers

Integrating RJMCMC and Kalman filters for multiple object tracking

Abstract : In this paper, we propose to integrate the Kalman filter with the reversible jump Markov Chain Monte Carlo (RJMCMC) sampler to improve the optimization procedure in the case of multiple object tracking. We propose the use of a dedicated perturbation kernel that uses the Kalman filter to generate multiple objects in a single iteration. We demonstrate that this kernel reduces considerably the mixing time of the Markov chain, as compared to the standard RJMCMC sampler. We show results on two synthetic biological sequences and two simulated remotely sensed data sets of the city of Toulon, France.
Document type :
Conference papers
Complete list of metadata

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/hal-01168336
Contributor : Paula Craciun <>
Submitted on : Monday, June 29, 2015 - 9:28:39 AM
Last modification on : Thursday, March 5, 2020 - 4:52:03 PM
Long-term archiving on: : Wednesday, September 16, 2015 - 12:37:16 AM

File

GRETSI2015_final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01168336, version 1

Collections

Citation

Paula Craciun, Mathias Ortner, Josiane Zerubia. Integrating RJMCMC and Kalman filters for multiple object tracking. GRETSI – Traitement du Signal et des Images, Sep 2015, Lyon, France. ⟨hal-01168336⟩

Share

Metrics

Record views

224

Files downloads

343