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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Appearance-based Tracking of Persons with an Omnidirectional Vision Sensor




    Publication date :

    2003-06-01


    Size :

    472768 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    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