Stixels have been successfully applied to a wide range of vision tasks in autonomous driving, recently including instance segmentation. However, due to their sparse occurrence in the image, until now Stixels seldomly served as input for Deep Learning algorithms, restricting their utility for such approaches. In this work we present StixelPointNet, a novel method to perform fast instance segmentation directly on Stixels. By regarding the Stixel representation as unstructured data similar to point clouds, architectures like PointNet are able to learn features from Stixels. We use a bounding box detector to propose candidate instances, for which the relevant Stixels are extracted from the input image. On these Stixels, a PointNet models learns binary segmentations, which we then unify throughout the whole image in a final selection step. StixelPointNet achieves state-of-the-art performance on Stixel-level, is considerably faster than pixel-based segmentation methods, and shows that with our approach the Stixel domain can be introduced to many new 3D Deep Learning tasks.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning Stixel-based Instance Segmentation


    Beteiligte:
    Santarossa, Monty (Autor:in) / Schneider, Lukas (Autor:in) / Zelenka, Claudius (Autor:in) / Schmarje, Lars (Autor:in) / Koch, Reinhard (Autor:in) / Franke, Uwe (Autor:in)


    Erscheinungsdatum :

    2021-07-11


    Format / Umfang :

    4929954 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    SPIDER-BASED STIXEL OBJECT SEGMENTATION

    Erbs, F. / Witte, A. / Scharwaechter, T. et al. | British Library Conference Proceedings | 2014


    STIXEL ESTIMATION AND ROAD SCENE SEGMENTATION USING DEEP LEARNING

    LEVI DAN / GARNETT NOA | Europäisches Patentamt | 2016

    Freier Zugriff

    Efficient Stixel-Based Object Recognition

    Enzweiler, M. / Hummel, M. / Pfeiffer, D. et al. | British Library Conference Proceedings | 2012


    Efficient Stixel-based object recognition

    Enzweiler, Markus / Hummel, Matthias / Pfeiffer, David et al. | IEEE | 2012


    Moving Vehicle Detection by Optimal Segmentation of the Dynamic Stixel World

    Erbs, F. / Barth, A. / Franke, U. et al. | British Library Conference Proceedings | 2011