Accurate detection of obstacles in 3D is an essential task for autonomous driving and intelligent transportation. In this work, we propose a general multimodal fusion framework FusionPainting to fuse the 2D RGB image and 3D point clouds at a semantic level for boosting the 3D object detection task. Especially, the FusionPainting framework consists of three main modules: a multi-modal semantic segmentation module, an adaptive attention-based semantic fusion module, and a 3D object detector. First, semantic information is obtained for 2D image and 3D Lidar point clouds based on 2D and 3D segmentation approaches. Then the segmentation results from different sensors are adaptively fused based on the proposed attention-based semantic fusion module. Finally, the point clouds painted with the fused semantic label are sent to the 3D detector for obtaining the 3D objection results. The effectiveness of the proposed framework has been verified on the large-scale nuScenes detection benchmark by comparing with three different baselines. The experimental results show that the fusion strategy can significantly improve the detection performance compared to the methods using only point clouds, and the methods using point clouds only painted with 2D segmentation information. Furthermore, the proposed approach outperforms other state-of-the-art methods on the nuScenes testing benchmark. Code will be available at https://github.com/Shaoqing26/FusionPainting/.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detection


    Contributors:
    Xu, Shaoqing (author) / Zhou, Dingfu (author) / Fang, Jin (author) / Yin, Junbo (author) / Bin, Zhou (author) / Zhang, Liangjun (author)


    Publication date :

    2021-09-19


    Size :

    3710821 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    GFD-Retina: Gated Fusion Double RetinaNet for Multimodal 2D Road Object Detection

    Condat, Robin / Rogozan, Alexandrina / Bensrhair, Abdelaziz | IEEE | 2020


    Point-Voxel Fusion for Multimodal 3D Detection

    Wang, Ke / Zhang, Zhichuang | IEEE | 2022


    Gesture Recognition in Robotic Surgery with Multimodal Attention

    Van Amsterdam, B / Funke, I / Edwards, E et al. | BASE | 2022

    Free access

    AMMF: Attention-Based Multi-Phase Multi-Task Fusion for Small Contour Object 3D Detection

    Xie, Bangquan / Yang, Zongming / Yang, Liang et al. | IEEE | 2023