LiDAR-based 3D object detection is essential for autonomous driving. In order to extract information from sparse and unordered point cloud data, pillar-based methods make the data compact and orderly by converting point cloud into pseudo images. However, these methods suffer from limited feature extraction capabilities, and tend to lose key information during the conversion, leading to inferior detection accuracy than voxel-based or point-based methods especially for small objects. In this paper, we propose SCNet3D, a novel pillar-based method that tackles the challenges of feature enhancement, information preservation, and small target detection from the perspectives of features and data. We first introduce a Feature Enhancement Module (FEM), which uses the attention mechanism to weight features in three dimensions, and enhances 3D features from local to global layer by layer. Then, a STMod-Convolution Network (SCNet) is designed, which achieves sufficient feature extraction and fusion of BEV pseudo images through two channels, one for basic feature and one for advanced feature. Moreover, a Shape and Distance Aware Data Augmentation (SDAA) approach is proposed to add more samples to the point cloud while maintaining the original shape and distance of the samples during the training process. Extensive experiments demonstrate that our SCNet3D has superior performance and excellent robustness. Remarkably, SCNet3D achieves the AP of 82.35% in the moderate Car category, 44.64% in the moderate Pedestrian category and 67.55% in the moderate Cyclist category on the KITTI test split in 3D detection benchmark, outperforming many state-of-the-art 3D detectors.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    SCNet3D: Rethinking the Feature Extraction Process of Pillar-Based 3D Object Detection


    Beteiligte:
    Li, Junru (Autor:in) / Wang, Zhiling (Autor:in) / Gong, Diancheng (Autor:in) / Wang, Chunchun (Autor:in)


    Erscheinungsdatum :

    01.01.2025


    Format / Umfang :

    5546973 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    RPFA-Net: a 4D RaDAR Pillar Feature Attention Network for 3D Object Detection

    Xu, Baowei / Zhang, Xinyu / Wang, Li et al. | IEEE | 2021


    OBJECT FEATURE EXTRACTION SYSTEM

    SHIMANO SHUNNOSUKE / YAMAGUCHI AKIO / KUME TAKESHI | Europäisches Patentamt | 2017

    Freier Zugriff

    OBJECT FEATURE EXTRACTION SYSTEM

    SHIMANO SHUNNOSUKE / YAMAGUCHI AKIO / KUME TAKESHI | Europäisches Patentamt | 2017

    Freier Zugriff

    Rethinking Self-Attention for Multispectral Object Detection

    Hu, Sijie / Bonardi, Fabien / Bouchafa, Samia et al. | IEEE | 2024


    Object contour extraction based on image feature analysis

    Wang, Tian / Zou, Zilong / Qiao, Meina | British Library Online Contents | 2016