The detection of motion and moving objects or persons with stationary monocular cameras has been extensively studied. However, those techniques fail if the camera is moving itself. In this paper, we present a method for detecting and estimating the position of moving objects using a monocular camera that is mounted in front of a mobile robot platform. The position estimates are used for obstacle avoidance and robot navigation. We apply image warping to compensate the egomotion of the camera. This allows us to use standard techniques for motion detection. The final position and velocity estimates are obtained using Extended Kalman Filters. Combined with a monocular scene reconstruction our approach allows the robust detection and avoidance of both static and moving obstacles by using a single monocular camera as the only sensor.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Monocular detection and estimation of moving obstacles for robot navigation


    Beteiligte:

    Erscheinungsdatum :

    2012-02-23


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    620 / 629



    Robot Motion Planning Among Moving Obstacles

    Fiorini, P. / Shiller, Z. | NTRS | 1995


    Automatic Detection of Obstacles in Railway Tracks Using Monocular Camera

    Kano, Guilherme / Andrade, Tiago / Moutinho, Alexandra | British Library Conference Proceedings | 2019


    Robot Local Motion Planning among Moving Obstacles

    Kreczmer, B. / IEEE | British Library Conference Proceedings | 2005


    Monocular Vision for Mobile Robot Localization and Autonomous Navigation

    Royer, E. / Lhuillier, M. / Dhome, M. et al. | British Library Online Contents | 2007