Particle Markov Chain Monte Carlo for Bayesian Multi-Target Tracking

A.-T. Vu, Ba-Ngu Vo, R. Evans

    Research output: Chapter in Book/Conference paperConference paperpeer-review

    Abstract

    We propose a new multi-target tracking (MTT) algorithm capable of tracking an unknown number of targets that move close and/or cross each other in a dense environment. The optimal Bayes MTT problem is formulated in the Random Finite Set framework and Particle Markov Chain Monte Carlo (PMCMC) is applied to compute the multi-target posterior distribution. The PMCMC technique is a combination of Markov chain Monte Carlo (MCMC) and sequential Monte Carlo methods to design an efficient high dimensional proposal distributions for MCMC algorithms. This technique allows our multi-target tracker to handle high track densities in a computationally feasible manner. Our simulations show that under scenarios with a large number of closely spaced tracks the estimated number of tracks and their trajectories are reliable.
    Original languageEnglish
    Title of host publication2011 Proceedings of the 14th International Conference on Information Fusion (FUSION)
    Place of PublicationUnited States
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages1-8
    Volume1
    ISBN (Print)9780982443828
    Publication statusPublished - 2011
    Event14th International Conference on Information Fusion - Chicago, United States
    Duration: 5 Jul 20118 Jul 2011

    Conference

    Conference14th International Conference on Information Fusion
    Abbreviated titleFUSION 2011
    Country/TerritoryUnited States
    CityChicago
    Period5/07/118/07/11

    Fingerprint

    Dive into the research topics of 'Particle Markov Chain Monte Carlo for Bayesian Multi-Target Tracking'. Together they form a unique fingerprint.

    Cite this