LiDAR and camera fusion have emerged as a promising approach for improving place recognition in robotics and autonomous vehicles. However, most existing approaches often treat sensors separately, overlooking the potential benefits of correlation between them. In this paper, we propose a Cross- Modality Module (CMM) to leverage the potential correlation of LiDAR and camera features for place recognition. Besides, to fully exploit potential of each modality, we propose a Local-Global Fusion Module to supplement global coarse-grained features with local fine-grained features. The experiment results on public datasets demonstrate that our approach effectively improves the average recall by 2.3%, reaching 98.7%, compared with simply stacking of LiDAR and camera.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    CMM: LiDAR-Visual Fusion with Cross-Modality Module for Large-Scale Place Recognition


    Weitere Titelangaben:

    Sae Technical Papers


    Beteiligte:
    Li, Bin (Autor:in) / Lu, Fan (Autor:in) / Chen, Guang (Autor:in) / Xue, Shijie (Autor:in) / Liu, Zhengfa (Autor:in)

    Kongress:

    SAE 2023 Intelligent and Connected Vehicles Symposium ; 2023



    Erscheinungsdatum :

    2023-12-20




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch





    Visual Place Recognition in Long-term and Large-scale Environment based on CNN Feature

    Zhu, Jianliang / Ai, Yunfeng / Tian, Bin et al. | IEEE | 2018


    Incremental Cross-Modality deep learning for pedestrian recognition

    Pop, Danut Ovidiu / Rogozan, Alexandrina / Nashashibi, Fawzi et al. | IEEE | 2017


    ImageNet Large Scale Visual Recognition Challenge

    Russakovsky, O. / Deng, J. / Su, H. et al. | British Library Online Contents | 2015


    Pedestrian recognition through different cross-modality deep learning methods

    Pop, Danut Ovidiu / Rogozan, Alexandrina / Nashashibi, Fawzi et al. | IEEE | 2017