This paper addresses the problem of real-time 3D model-based tracking by combining point-based and edge-based tracking systems. We present a careful analysis of the properties of these two sensor systems and show that this leads to some non -trivial design choices that collectively yield extremely high performance. In particular, we present a method for integrating the two systems and robustly combining the pose estimates they produce. Further we show how on-line learning can be used to improve the performance of feature tracking. Finally, to aid real-time performance, we introduce the FAST feature detector which can perform full-frame feature detection at 400Hz. The combination of these techniques results in a system which is capable of tracking average prediction errors of 200 pixels. This level of robustness allows us to track very rapid motions, such as 50/spl deg/ camera shake at 6Hz.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Fusing points and lines for high performance tracking


    Beteiligte:
    Rosten, E. (Autor:in) / Drummond, T. (Autor:in)


    Erscheinungsdatum :

    01.01.2005


    Format / Umfang :

    2791378 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Fusing Points and Lines for High Performance Tracking

    Rosten, E. / Drummond, T. / IEEE | British Library Conference Proceedings | 2005


    Driver Activity Recognition by Fusing Multi-object and Key Points Detection

    Pardo-Decimavilla, Pablo / Bergasa, Luis M. / López-Guillén, Elena et al. | Springer Verlag | 2024


    FUSING OPTICAL FLOW AND STEREO DISPARITY FOR OBJECT TRACKING

    Dang, T. / Hoffmann, C. / Stiller, C. et al. | British Library Conference Proceedings | 2002


    Fusing optical flow and stereo disparity for object tracking

    Dang, T. / Hoffmann, C. / Stiller, C. | IEEE | 2002


    Collar Fusing

    British Library Online Contents | 1997