Modern efficient Convolutional Neural Networks (CNNs) are able to perform semantic segmentation both swiftly and accurately, which covers typically separate detection tasks desired by Intelligent Vehicles (IV) in a unified way. Most of the current semantic perception frameworks are designed to work with pinhole cameras and benchmarked against public datasets with narrow Field-of-View (FoV) images. However, there is a large accuracy downgrade when a pinhole-yielded CNN is taken to omnidirectional imagery, causing it unreliable for surrounding perception. In this paper, we propose an omnisupervised learning framework for efficient CNNs, which bridges multiple heterogeneous data sources that are already available in the community, bypassing the labor-intensive process to have manually annotated panoramas, while improving their reliability in unseen omnidirectional domains. Being omnisupervised, the efficient CNN exploits both labeled pinhole images and unlabeled panoramas. The framework is based on our specialized ensemble method that considers the wide-angle and wrap-around features of omnidirectional images, to automatically generate panoramic labels for data distillation. A comprehensive variety of experiments demonstrates that the proposed solution helps to attain significant generalizability gains in panoramic imagery domains. Our approach outperforms state-of-the-art efficient segmenters on highly unconstrained IDD20K and PASS datasets.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Omnisupervised Omnidirectional Semantic Segmentation


    Beteiligte:
    Yang, Kailun (Autor:in) / Hu, Xinxin (Autor:in) / Fang, Yicheng (Autor:in) / Wang, Kaiwei (Autor:in) / Stiefelhagen, Rainer (Autor:in)


    Erscheinungsdatum :

    01.02.2022


    Format / Umfang :

    16715257 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    OMNIDIRECTIONAL PLATFORM AND OMNIDIRECTIONAL TRANSPORTER

    CANUTO GIL JUAN JOSÉ / DOMENECH MESTRES CARLES | Europäisches Patentamt | 2021

    Freier Zugriff

    OMNIDIRECTIONAL WHEEL AND OMNIDIRECTIONAL MOVING BODY

    TADAKUMA KENJIRO / TAKANE ERI / KONYO MASASHI et al. | Europäisches Patentamt | 2017

    Freier Zugriff

    Omnidirectional wheel and scooter having omnidirectional wheel

    SHI XIUYU / YANG LEI | Europäisches Patentamt | 2024

    Freier Zugriff

    OMNIDIRECTIONAL WHEEL AND SCOOTER HAVING OMNIDIRECTIONAL WHEEL

    SHI XIUYU / YANG LEI | Europäisches Patentamt | 2022

    Freier Zugriff

    OMNIDIRECTIONAL WHEEL ASSEMBLY AND OMNIDIRECTIONAL VEHICLE

    GANO JOHN VICTOR / SCALABRONI ENRIQUE HECTOR | Europäisches Patentamt | 2015

    Freier Zugriff