Scene flow methods estimate the three-dimensional motion field for points in the world, using multi-camera video data. Such methods combine multi-view reconstruction with motion estimation approaches. This paper describes an alternative formulation for dense scene flow estimation that provides convincing results using only two cameras by fusing stereo and optical flow estimation into a single coherent framework. To handle the aperture problems inherent in the estimation task, a multi-scale method along with a novel adaptive smoothing technique is used to gain a regularized solution. This combined approach both preserves discontinuities and prevents over-regularization - two problems commonly associated with basic multi-scale approaches. Internally, the framework generates probability distributions for optical flow and disparity. Taking into account the uncertainty in the intermediate stages allows for more reliable estimation of the 3D scene flow than standard stereo and optical flow methods allow. Experiments with synthetic and real test data demonstrate the effectiveness of the approach.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Multi-Scale 3D Scene Flow from Binocular Stereo Sequences


    Beteiligte:
    Li, Rui (Autor:in) / Sclaroff, Stan (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    4306987 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Multi-scale 3D scene flow from binocular stereo sequences

    Li, R. / Sclaroff, S. | British Library Online Contents | 2008


    Binocular Stereo from Grey-Scale Images

    Nielsen, M. / Maas, R. / Niessen, W. J. et al. | British Library Online Contents | 1999


    Binocular Spherical Stereo

    Li, S. | Online Contents | 2008


    Binocular Spherical Stereo

    Shigang Li, | IEEE | 2008


    Occlusions and Binocular Stereo

    Geiger, D. / Ladendorf, B. / Yuille, A. | British Library Online Contents | 1995