This paper presents a particle swarm optimization (PSO) based approach for multiple object tracking based on histogram matching. To start with, gray-level histograms are calculated to establish a feature model for each of the target object. The difference between the gray-level histogram corresponding to each particle in the search space and the target object is used as the fitness value. Multiple swarms are created depending on the number of the target objects under tracking. Because of the efficiency and simplicity of the PSO algorithm for global optimization, target objects can be tracked as iterations continue. Experimental results confirm that the proposed PSO algorithm can rapidly converge, allowing real-time tracking of each target object. When the objects being tracked move outside the tracking range, global search capability of the PSO resumes to re-trace the target objects.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Multiple Object Tracking using Particle Swarm Optimization


    Beteiligte:
    Chen-Chien Hsu (Autor:in) / Guo-Tang Dai (Autor:in)

    Erscheinungsdatum :

    21.08.2012


    Anmerkungen:

    oai:zenodo.org:1075523



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629 / 620





    Multiple object tracking using particle filters

    Jaward, M. / Mihaylova, L. / Canagarajah, N. et al. | IEEE | 2006


    Multiple UAV Task Allocation Using Particle Swarm Optimization

    Sujit, P / George, Joel / Beard, Randy | AIAA | 2008


    Multiple UAV Task Allocation Using Particle Swarm Optimization

    Sujit, P. / George, J. / Beard, R. et al. | British Library Conference Proceedings | 2008


    Trajectory tracking control based on improved particle swarm optimization

    Wang, Yuxiao / Chao, Tao / Wang, Songyan et al. | IEEE | 2016