A 360° perception of scene geometry is essential for automated driving, notably for parking and urban driving scenarios. Typically, it is achieved using surround-view fisheye cameras, focusing on the near-field area around the vehicle. The majority of current depth estimation approaches focus on employing just a single camera, which cannot be straightforwardly generalized to multiple cameras. The depth estimation model must be tested on a variety of cameras equipped to millions of cars with varying camera geometries. Even within a single car, intrinsics vary due to manufacturing tolerances. Deep learning models are sensitive to these changes, and it is practically infeasible to train and test on each camera variant. As a result, we present novel camera-geometry adaptive multi-scale convolutions which utilize the camera parameters as a conditional input, enabling the model to generalize to previously unseen fisheye cameras. Additionally, we improve the distance estimation by pairwise and patchwise vector-based self-attention encoder networks. We evaluate our approach on the Fisheye WoodScape surround-view dataset, significantly improving over previous approaches. We also show a generalization of our approach across different camera viewing angles and perform extensive experiments to support our contributions. To enable comparison with other approaches, we evaluate the front camera data on the KITTI dataset (pinhole camera images) and achieve state-of-the-art performance among self-supervised monocular methods. An overview video with qualitative results is provided at https://youtu.be/bmX0UcU9wtA. Baseline code and dataset will be made public.1


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras


    Beteiligte:
    Ravi Kumar, Varun (Autor:in) / Klingner, Marvin (Autor:in) / Yogamani, Senthil (Autor:in) / Bach, Markus (Autor:in) / Milz, Stefan (Autor:in) / Fingscheidt, Tim (Autor:in) / Mader, Patrick (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2022-08-01


    Format / Umfang :

    2883482 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Near-Field Perception for Low-Speed Vehicle Automation Using Surround-View Fisheye Cameras

    Eising, Ciaran / Horgan, Jonathan / Yogamani, Senthil | IEEE | 2022


    Multi-task near-field perception for autonomous driving using surround-view fisheye cameras

    Ravi Kumar, Varun / Technische Universität Ilmenau | TIBKAT | 2021

    Freier Zugriff

    Machine Learning-based Stereo Vision Algorithm for Surround View Fisheye Cameras

    Akita, Tokihiko / Yamauchi, Yuji / Fujiyoshi, Hironobu | IEEE | 2018


    An Online Learning System for Wireless Charging Alignment Using Surround-View Fisheye Cameras

    Dahal, Ashok / Kumar, Varun Ravi / Yogamani, Senthil et al. | IEEE | 2022


    Surround-View Fisheye Camera Perception for Automated Driving: Overview, Survey & Challenges

    Kumar, Varun Ravi / Eising, Ciaran / Witt, Christian et al. | IEEE | 2023

    Freier Zugriff