This paper addresses the problem of tracking a moving person with a single, omnidirectional camera. An appearance-based tracking system is described which uses a self-acquired appearance model and a Kalman filter to estimate the position of the person. Features corresponding to "depth cues" are first extracted from the panoramic images, then an artificial neural network is trained to estimate the distance of the person from the camera. The estimates are combined using a discrete Kalman filter to track the position of the person over time. The ground truth information required for training the neural network and the experimental analysis was obtained from another vision system, which uses multiple webcams and triangulation to calculate the true position of the person. Experimental results show that the tracking system is accurate and reliable, and that its performance can be further improved by learning multiple, person-specific appearance models.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Appearance-based Tracking of Persons with an Omnidirectional Vision Sensor


    Beteiligte:


    Erscheinungsdatum :

    01.06.2003


    Format / Umfang :

    472768 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    A Distributed Omnidirectional Vision Sensor

    Mordovanaki, A. / Lakshmanan, S. / INRIA et al. | British Library Conference Proceedings | 2003


    A distributed omnidirectional vision sensor

    Mordovanaki, A.G. / Lakshmanan, S. | IEEE | 2002



    Omnidirectional Vision Based Topological Navigation

    Goedemé, T. / Nuttin, M. / Tuytelaars, T. et al. | British Library Online Contents | 2007


    Autonomous MAV guidance with a lightweight omnidirectional vision sensor

    Moore, Richard J. D. / Dantu, Karthik / Barrows, Geoffrey L. et al. | IEEE | 2014