Optical flow estimation is a basic task in self-driving and robotics systems, which enables to temporally interpret traffic scenes. Autonomous vehicles clearly benefit from the ultra-wide Field of View (FoV) offered by 360° panoramic sensors. However, due to the unique imaging process of panoramic cameras, models designed for pinhole images do not directly generalize satisfactorily to 360° panoramic images. In this paper, we put forward a novel network framework——PANO FLOW, to learn optical flow for panoramic images. To overcome the distortions introduced by equirectangular projection in panoramic transformation, we design a Flow Distortion Augmentation (FDA) method, which contains radial flow distortion (FDA-R) or equirectangular flow distortion (FDA-E). We further look into the definition and properties of cyclic optical flow for panoramic videos, and hereby propose a Cyclic Flow Estimation (CFE) method by leveraging the cyclicity of spherical images to infer 360° optical flow and converting large displacement to relatively small displacement. PanoFlow is applicable to any existing flow estimation method and benefits from the progress of narrow-FoV flow estimation. In addition, we create and release a synthetic panoramic dataset FlowScape based on CARLA to facilitate training and quantitative analysis. PanoFlow achieves state-of-the-art performance on the public OmniFlowNet and the fresh established FlowScape benchmarks. Our proposed approach reduces the End-Point-Error (EPE) on FlowScape by 27.3%. On OmniFlowNet, PanoFlow achieves an EPE of 3.17 pixels, a 55.5% error reduction from the best published result (7.12 pixels). We also qualitatively validate our method via an outdoor collection vehicle and a public real-world OmniPhotos dataset, indicating strong potential and robustness for real-world navigation applications. Code and dataset are publicly available at PanoFlow.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    PanoFlow: Learning 360° Optical Flow for Surrounding Temporal Understanding


    Beteiligte:
    Shi, Hao (Autor:in) / Zhou, Yifan (Autor:in) / Yang, Kailun (Autor:in) / Yin, Xiaoting (Autor:in) / Wang, Ze (Autor:in) / Ye, Yaozu (Autor:in) / Yin, Zhe (Autor:in) / Meng, Shi (Autor:in) / Li, Peng (Autor:in) / Wang, Kaiwei (Autor:in)


    Erscheinungsdatum :

    2023-05-01


    Format / Umfang :

    4929673 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Optical environment surrounding the MSX spacecraft

    Green, B. D. | British Library Online Contents | 1997


    Air Flow Surrounding Burning Transient Diesel Sprays

    Rhim, Dong-Ryul / Farrell, Patrick V. | SAE Technical Papers | 2002


    Commercial vehicle full-surrounding turbulent flow cover

    HAO JIANGAN / ZHANG RUIJUN / LI JIANHENG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    SURROUNDING MONITORING DEVICE, SURROUNDING MONITORING METHOD AND SURROUNDING MONITORING PROGRAM

    HORI TOSHIHIKO / MATSUSHIMA SADAHISA / INOUE DAISUKE et al. | Europäisches Patentamt | 2022

    Freier Zugriff