In this paper we propose a fast fully convolutional neural network for panoptic segmentation that can provide an accurate semantic and instance-level representation of the environment in the 2D space. We tackle panoptic segmentation as a dense classification problem and generate masks for stuff classes as well as for each instance of things classes. Our network employs a shared backbone and Feature Pyramid Network for multi-scale feature extraction which we extend with dual-decoders that learn background and foreground specific masks. Guided by object proposals, the panoptic head assembles location-sensitive prototype masks using a learned weighting scheme. Our solution runs in real-time, in 82 ms on high resolution images, making it suitable for robotic applications and automated driving. Extensive experiments on the Cityscapes dataset demonstrate that our panoptic segmentation network is robust and accurate, with 57.3% PQ and 76.9% mIoU.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Real-Time Panoptic Segmentation with Prototype Masks for Automated Driving


    Beteiligte:


    Erscheinungsdatum :

    19.10.2020


    Format / Umfang :

    1954233 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    REAL-TIME PANOPTIC SEGMENTATION WITH PROTOTYPE MASKS FOR AUTOMATED DRIVING

    Petrovai, Andra / Nedevschi, Sergiu | British Library Conference Proceedings | 2020


    Multi-task Network for Panoptic Segmentation in Automated Driving

    Petrovai, Andra / Nedevschi, Sergiu | IEEE | 2019


    Panoptic Segmentation from Stitched Panoramic View for Automated Driving

    Kinzig, Christian / Miller, Henning / Lauer, Martin et al. | IEEE | 2024


    Depth-Aware Panoptic Segmentation with Mask Transformers and Panoptic Bins for Autonomous Driving

    Petrovai, Andra / Miclea, Vlad-Cristian / Nedevschi, Sergiu | IEEE | 2024


    The Effect of Camera Data Degradation Factors on Panoptic Segmentation for Automated Driving

    Wang, Yiting / Zhao, Haonan / Debattista, Kurt et al. | IEEE | 2023