Only a few existing works exploit multiple modalities of data for road detection task in the context of autonomous driving. In this work, a deep learning based approach is developed to fuse LIDAR point cloud and camera image features over a bird's eye view representation. A two-stream fully-convolutional network is designed as encoder to extract general features of two types of data. Instead of limiting the fusion processing at a single stage or to a predefined extent, we propose a multi-stage residual fusion strategy to merge the feature maps in a residual learning fashion, and integrate the information at different network depth. Experiments conduct on KITTI road benchmark show that our proposed method has a significant improvement over single modality methods and other fusion approaches. And it is also among the top-performing algorithms.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-Stage Residual Fusion Network for LIDAR-Camera Road Detection


    Contributors:
    Yu, Dameng (author) / Xiong, Hui (author) / Xu, Qing (author) / Wang, Jianqiang (author) / Li, Keqiang (author)


    Publication date :

    2019-06-01


    Size :

    577537 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    MULTI-STAGE RESIDUAL FUSION NETWORK FOR LIDAR-CAMERA ROAD DETECTION

    Yu, Dameng / Xiong, Hui / Xu, Qing et al. | British Library Conference Proceedings | 2019


    Road perception and road line detection based on fusion of LiDAR and camera

    Fan, Yimei / Yu, Xin / Xu, Nana et al. | SPIE | 2022




    Multi-Classifier Based LIDAR and Camera Fusion

    Hwang, Jae Pil / Cho, Seung Eun / Ryu, Kyung Jin et al. | IEEE | 2007