Instance segmentation is an important task for the interpretation of images in the area of autonomous or assisted driving applications. Not only indicating the semantic class for each pixel of an image, but also separating different instances of the same class, even if neighboring in the image, it can replace a multi-class object detector. In addition, it offers a better localization of objects in the image by replacing the object detector bounding box with a fine-grained object shape. The recently presented Cityscapes dataset promoted this topic by offering a large set of data labeled at pixel level. Building on the previous work of (Uhrig et al., 2016), this work proposes two improvements compared to this baseline strategy leading to significant performance improvements. First, a better distance measure for angular differences, which is unaffected by the -p/p discontinuity, is proposed. This leads to improved object center localization. Second, the imagery from vehicle perspective includes a fixed vanishing point. A foveal concept counteracts the fact that objects get smaller in the image towards this point. This strategy especially improves the results for small objects in large distances from the vehicle.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Foveal vision for instance segmentation of road images


    Beteiligte:
    Ortelt, B. (Autor:in) / Herrmann, C. (Autor:in) / Willersinn, Dieter (Autor:in) / Beyerer, Jürgen (Autor:in)

    Kongress:

    2018


    Erscheinungsdatum :

    2018


    Format / Umfang :

    8 pages



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt



    VLSI Implementation of a Foveal Polygon Segmentation Algorithm

    Coslado, F. / Camacho, P. / Gonzales, M. et al. | British Library Conference Proceedings | 1999


    Strategies for object manipulation using foveal and peripheral vision

    Kragic, Danica / Björkman, Mårten | BASE | 2006

    Freier Zugriff



    Rock Instance Segmentation from Synthetic Images for Planetary Exploration Missions

    Boerdijk, Wout / Müller, Marcus Gerhard / Durner, Maximilian et al. | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2021

    Freier Zugriff