A real-time semantic 3D occupancy mapping framework is proposed in this paper. The framework is based on the Bayesian kernel inference strategy. Two novel free space representations are proposed to efficiently construct training data and improve the mapping speed, which is a major bottleneck for real-world deployments. Our method achieves real-time mapping even on a consumer-grade CPU. Another important benefit is that our method can handle dynamic scenarios, due to the coverage completeness of the proposed algorithm. Experiments on real-world point cloud scan datasets are presented.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Real-time Semantic 3D Dense Occupancy Mapping with Efficient Free Space Representations


    Beteiligte:
    Zhong, Yuanxin (Autor:in) / Peng, Huei (Autor:in)


    Erscheinungsdatum :

    2022-10-08


    Format / Umfang :

    3013776 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Real-time Occupancy Mapping System for Autonomous Vehicles

    MISHRA LALAN JEE / WIETFELDT RICHARD DOMINIC / CZOMPO JOSEPH | Europäisches Patentamt | 2016

    Freier Zugriff

    Virtual occupancy for real-time occupancy information in buildings

    Zhao, Y. / Zeiler, W. / Boxem, G. et al. | BASE | 2015

    Freier Zugriff

    Real-time Omnidirectional Visual SLAM with Semi-Dense Mapping

    Wangl, Senbo / Yuel, Jiguang / Dong, Yanchao et al. | IEEE | 2018


    Conditional Monte Carlo Dense Occupancy Tracker

    Rummelhard, Lukas / Negre, Amaury / Laugier, Christian | IEEE | 2015


    Towards real-time dense 3D mapping with lightweight portable sensors

    Hamesse, Charles / Haelterman, Rob / Luong, Hiep | BASE | 2022

    Freier Zugriff