Airport ground operations must be safe and should avoid capacity backlogs. To that end, the availability of reliable surveillance data capturing important semantic information about the local traffic situation and the operating conditions on the apron and the maneuvering area are essential. Along those lines, LiDAR sensors combined with computer vision algorithms for semantic scene understanding were recently identified to offer a cost-effective, noncooperative surveillance solution that is expected to contribute to the operational goals mentioned above. However little work exists dealing with fast and accurate LiDAR semantic segmentation of such environments. This is partly due to the fact, that state-of-the-art algorithms in LiDAR semantic segmentation heavily rely on large-scale data sets with fine-grained labels. Although some hand-labeled data sets are publicly available, the point-wise annotation of 3D point clouds requires painstakingly work that is extremely cumbersome. Consequently, we propose a simulation-based approach to generate synthetic training data of the apron using a virtual airport environment that integrates a LiDAR sensor model. In this way, arbitrary scenarios captured under different operational conditions including static objects and moving aircraft provide labeled point data. This way, we trained and tested successfully a LiDAR semantic segmentation model emphasizing on aircraft approaching/leaving the gate after arrival/departure, thin structures (poles), airport buildings, and ground-plane. The developed technique provides an important baseline for the expected performance of the trained model on real data. We believe that the resulting framework provides additional visual cues capturing relevant semantic information that potentially assist the controller in complex situations.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    3D Modeling of the airport environment for fast and accurate LiDAR semantic segmentation of apron operations


    Beteiligte:


    Erscheinungsdatum :

    11.10.2020


    Format / Umfang :

    3507627 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Airport apron

    LIN JINGYI | Europäisches Patentamt | 2024

    Freier Zugriff

    APRON GATE AT AN AIRPORT

    ESPINA MANUEL HERNÁNDEZ / BERMEJO ANTONIO MURIAS / ORTEGA JAIRO GRANDA et al. | Europäisches Patentamt | 2018

    Freier Zugriff

    Flight apron -- Oakland international airport

    Engineering Index Backfile | 1963


    Enhanced Surveillance and Conflict Prediction for Airport Apron Operation using LiDAR Sensing

    Braßel, Hannes / Technische Universität Dresden | TIBKAT | 2024

    Freier Zugriff

    APRON GATE AT AN AIRPORT

    HERNÁNDEZ ESPINA MANUEL / MURIAS BERMEJO ANTONIO / GRANDA ORTEGA JAIRO et al. | Europäisches Patentamt | 2018

    Freier Zugriff