State-of-the-art stixel methods fuse dense stereo and semantic class information, e.g. from a Convolutional Neural Network (CNN), into a compact representation of driveable space, obstacles, and background. However, they do not explicitly differentiate instances within the same class. We investigate several ways to augment single-frame stixels with instance information, which can similarly be extracted by a CNN from the color input. As a result, our novel Instance Stixels method efficiently computes stixels that do account for boundaries of individual objects, and represents individual instances as grouped stixels that express connectivity. Experiments on Cityscapes demonstrate that including instance information into the stixel computation itself, rather than as a post-processing step, increases Instance AP performance with approximately the same number of stixels. Qualitative results confirm that segmentation improves, especially for overlapping objects of the same class. Additional tests with ground truth instead of CNN output show that the approach has potential for even larger gains. Our Instance Stixels software is made freely available for non-commercial research purposes.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Instance Stixels: Segmenting and Grouping Stixels into Objects


    Beteiligte:


    Erscheinungsdatum :

    01.06.2019


    Format / Umfang :

    3492318 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Fast and Compact Image Segmentation Using Instance Stixels

    Hehn, Thomas / Kooij, Julian / Gavrila, Dariu | IEEE | 2022


    From stixels to objects — A conditional random field based approach

    Erbs, Friedrich / Schwarz, Beate / Franke, Uwe | IEEE | 2013



    Ef_; Cient Representation of Traf_; C Scenes by Means of Dynamic Stixels, pp. 217-224

    Pfeiffer, D. / Franke, U. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2010


    GROUPING OF MOVING OBJECTS

    TOKUNAGA ASUKA / HOSOKAWA SATOSHI / WATANABE SHOICHIRO et al. | Europäisches Patentamt | 2020

    Freier Zugriff