Point cloud, an efficient 3D object representation, plays an indispensable role in autonomous driving technologies, such as object avoidance, localization, and map building. The analysis of point clouds (e.g., 3D segmentation) is essential to exploit the informative value of point clouds for such applications. The main challenge remains to effectively and completely extract high-level point cloud feature representations. To this end, we present a novel multi-task Y-shaped graph neural network to explore 3D point clouds, referred to as MTYGNN. By extending the conventional U-Net, MTYGNN contains two main branches to simultaneously perform classification and segmentation tasks in point clouds. Meanwhile, the classification prediction is fused together with the semantic features as the scene context to make the segmentation task more accurate. Furthermore, we consider the homoscedastic uncertainty of each task to calculate the weights of multiple loss functions to ensure that tasks do not negatively interfere with each other. The proposed MTYGNN is evaluated on popular point cloud datasets in traffic scenarios. Experimental results demonstrate that our framework outperforms the state-of-the-art baseline methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Multi-Task Y-Shaped Graph Neural Network for Point Cloud Learning in Autonomous Driving


    Beteiligte:
    Zou, Xiaofeng (Autor:in) / Li, Kenli (Autor:in) / Li, Yangfan (Autor:in) / Wei, Wei (Autor:in) / Chen, Cen (Autor:in)


    Erscheinungsdatum :

    2022-07-01


    Format / Umfang :

    2398447 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Lidar Point Cloud Compression, Processing and Learning for Autonomous Driving

    Abbasi, Rashid / Bashir, Ali Kashif / Alyamani, Hasan J. et al. | IEEE | 2023


    Multi-task Learning with Future States for Vision-Based Autonomous Driving

    Kim, Inhan / Lee, Hyemin / Lee, Joonyeong et al. | British Library Conference Proceedings | 2021


    Point cloud processing for environmental analysis in Autonomous Driving using Deep Learning

    Simon, Martin / Technische Universität Ilmenau / Universitätsverlag Ilmenau | TIBKAT | 2023

    Freier Zugriff

    Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review

    Cui, Yaodong / Chen, Ren / Chu, Wenbo et al. | IEEE | 2022


    MTNAS: Search Multi-task Networks for Autonomous Driving

    Liu, Hao / Li, Dong / Peng, JinZhang et al. | British Library Conference Proceedings | 2021