Recently, 3D object detection based on deep learning has achieved impressive performance in complex indoor and outdoor scenes. Among the methods, the two-stage detection method performs the best; however, this method still needs improved accuracy and efficiency, especially for small size objects or autonomous driving scenes. In this paper, we propose an improved 3D object detection method based on a two-stage detector called the Improved Point-Voxel Region Convolutional Neural Network (IPV-RCNN). Our proposed method contains online training for data augmentation, upsampling convolution and k-means clustering for the bounding box to achieve 3D detection tasks from raw point clouds. The evaluation results on the KITTI 3D dataset show that the IPV-RCNN achieved a 96% mAP, which is 3% more accurate than the state-of-the-art detectors.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Improved Point-Voxel Region Convolutional Neural Network: 3D Object Detectors for Autonomous Driving


    Contributors:
    Li, Yujie (author) / Yang, Shuo (author) / Zheng, Yuchao (author) / Lu, Huimin (author)


    Publication date :

    2022-07-01


    Size :

    4654507 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    RefineNet: Refining Object Detectors for Autonomous Driving

    Rajaram, Rakesh Nattoji / Ohn-Bar, Eshed / Trivedi, Mohan Manubhai | IEEE | 2016



    Convolutional Neural Network Based on Self-Driving Autonomous Vehicle (CNN)

    Babu Naik, G. / Ameta, Prerit / Baba Shayeer, N. et al. | Springer Verlag | 2022


    LiDAR and Camera-Based Convolutional Neural Network Detection for Autonomous Driving

    Hamieh, Ismail / Myers, Ryan / Nimri, Hisham et al. | British Library Conference Proceedings | 2020


    LiDAR and Camera-Based Convolutional Neural Network Detection for Autonomous Driving

    Hamieh, Ismail / Myers, Ryan / Nimri, Hisham et al. | British Library Conference Proceedings | 2020