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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning Stixel-based Instance Segmentation


    Contributors:


    Publication date :

    2021-07-11


    Size :

    4929954 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    LEARNING STIXEL-BASED INSTANCE SEGMENTATION

    Santarossa, Monty / Schneider, Lukas / Zelenka, Claudius et al. | British Library Conference Proceedings | 2021


    SPIDER-BASED STIXEL OBJECT SEGMENTATION

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


    Spider-based Stixel object segmentation

    Erbs, Friedrich / Witte, Andreas / Scharwaechter, Timo et al. | IEEE | 2014


    STIXEL ESTIMATION AND ROAD SCENE SEGMENTATION USING DEEP LEARNING

    LEVI DAN / GARNETT NOA | European Patent Office | 2016

    Free access

    Efficient Stixel-based object recognition

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