Dense optical flow estimation is complex and time consuming, with state-of-the-art methods relying either on large synthetic data sets or on pipelines requiring up to a few minutes per frame pair. In this paper, we address the problem of optical flow estimation in the automotive scenario in a self-supervised manner. We argue that optical flow can be cast as a geometrical warping between two successive video frames and devise a deep architecture to estimate such transformation in two stages. First, a dense pixel-level flow is computed with a projective bootstrap on rigid surfaces. We show how such global transformation can be approximated with a homography and extend spatial transformer layers so that they can be employed to compute the flow field implied by such transformation. Subsequently, we refine the prediction by feeding a second, deeper network that accounts for moving objects. A final reconstruction loss compares the warping of frame $X_{t}$ with the subsequent frame $X_{t+1}$ and guides both estimates. The model has the speed advantages of end-to-end deep architectures while achieving competitive performances, both outperforming recent unsupervised methods and showing good generalization capabilities on new automotive data sets.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Self-Supervised Optical Flow Estimation by Projective Bootstrap


    Beteiligte:
    Alletto, Stefano (Autor:in) / Abati, Davide (Autor:in) / Calderara, Simone (Autor:in) / Cucchiara, Rita (Autor:in) / Rigazio, Luca (Autor:in)


    Erscheinungsdatum :

    01.09.2019


    Format / Umfang :

    3051593 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Bootstrap optical flow confidence and uncertainty measure

    Kybic, J. / Nieuwenhuis, C. | British Library Online Contents | 2011


    Reverse Optical Flow for Self-Supervised Adaptive Autonomous Robot Navigation

    Lookingbill, A. / Rogers, J. / Lieb, D. et al. | British Library Online Contents | 2007


    Self-supervised learning of scene flow

    ERWIN KRAFT | Europäisches Patentamt | 2023

    Freier Zugriff


    VEHICLE TRAILER ANGLE ESTIMATION VIA PROJECTIVE GEOMETRY

    LLANOS EDUARDO / IP JULIEN / FROEHLICH DOMINIK | Europäisches Patentamt | 2022

    Freier Zugriff