Pillar-based 3D detection simplifies the processing pipelines of feature extraction for irregular point clouds. However, the rigid voxelization adopted by pillar-based methods, inevitably and irreversibly, cuts off the direct connection between plenty of point pairs, thus hindering the modeling of local structures. Besides, it is difficult to handle intractable situations in 3D detection using structural information alone. In this paper, we propose a semantic-enhanced graph voxelization method to improve pillar-based feature extraction from two aspects, i.e., the construction of pillars and the learning of pillar-level features. For pillar construction, a novel voxelization method is proposed to capture more sufficient local structures with graph-based modeling of the relationships between adjacent point pairs. To learn representative features for each pillar, semantic enhancement is adopted by learning context awareness and class awareness pixel by pixel with a front-view-based segmentation branch. Extensive experiments conducted on the KITTI dataset demonstrate the effectiveness of the proposed method. Compared with the baseline, our method achieves 2.81 points and 2.65 points higher performance in 3D detection on KITTI test set for cars and cyclists individually.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Semantic-enhanced Graph Voxelization for Pillar-based 3D Detection from Point Clouds


    Contributors:
    Tian, Yonglin (author) / Wang, Xiao (author) / Shen, Yu (author) / Liu, Yuhang (author) / Wang, Zilei (author) / Wang, Fei-Yue (author)


    Publication date :

    2022-10-08


    Size :

    778935 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Fundamentals of Surface Voxelization

    Cohen-Or, D. / Kaufman, A. | British Library Online Contents | 1995


    Communication perception integrated scheduling method based on point cloud voxelization

    LUO GUIYANG / LI JINGLIN / YUAN QUAN et al. | European Patent Office | 2024

    Free access


    Graph based over-segmentation methods for 3D point clouds

    Ben-Shabat, Yizhak / Avraham, Tamar / Lindenbaum, Michael et al. | British Library Online Contents | 2018


    Exploiting Label Uncertainty for Enhanced 3D Object Detection From Point Clouds

    Sun, Yang / Lu, Bin / Liu, Yonghuai et al. | IEEE | 2024