Varying density of point clouds increases the difficulty of 3D detection. In this paper, we present a context-aware dynamic network (CADNet) to capture the variance of density by considering both point context and semantic context. Point-level contexts are generated from original point clouds to enlarge the effective receptive filed. They are extracted around the voxelized pillars based on our extended voxelization method and processed with the context encoder in parallel with the pillar features. With a large perception range, we are able to capture the variance of features for potential objects and generate attentive spatial guidance to help adjust the strengths for different regions. In the region proposal network, considering the limited representation ability of traditional convolution where same kernels are shared among different samples and positions, we propose a decomposable dynamic convolutional layer to adapt to the variance of input features by learning from the local semantic context. It adaptively generates the position-dependent coefficients for multiple fixed kernels and combines them to convolve with local features. Based on our dynamic convolution, we design a dual-path convolution block to further improve the representation ability. We conduct experiments on KITTI dataset and the proposed CADNet has achieved superior performance of 3D detection outperforming SECOND and PointPillars by a large margin at the speed of 30 FPS.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Context-Aware Dynamic Feature Extraction for 3D Object Detection in Point Clouds


    Contributors:
    Tian, Yonglin (author) / Huang, Lichao (author) / Yu, Hui (author) / Wu, Xiangbin (author) / Li, Xuesong (author) / Wang, Kunfeng (author) / Wang, Zilei (author) / Wang, Fei-Yue (author)


    Publication date :

    2022-08-01


    Size :

    24159606 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    An Extraction Algorithm for Sharp Feature Points from Point Clouds

    Wushour, S. / Cao, J. | British Library Online Contents | 2012


    Dynamic Feature Sharing for Cooperative Perception from Point Clouds

    Bai, Zhengwei / Wu, Guoyuan / Barth, Matthew J. et al. | IEEE | 2023


    SimLOG: Simultaneous Local-Global Feature Learning for 3D Object Detection in Indoor Point Clouds

    Wei, Mingqiang / Chen, Baian / Nan, Liangliang et al. | IEEE | 2024


    TOP-DOWN OBJECT DETECTION FROM LIDAR POINT CLOUDS

    SMOLYANSKIY NIKOLAI / OLDJA RYAN / CHEN KE et al. | European Patent Office | 2024

    Free access

    Top-down object detection from LiDAR point clouds

    SMOLYANSKIY NIKOLAI / OLDJA RYAN / CHEN KE et al. | European Patent Office | 2024

    Free access