Real-time and accurate 3-D object detection is one of the foundational technologies for environmental perception in autonomous vehicles. However, the existing second-stage anchor-based 3-D object detection algorithms have high accuracy, but they are challenging in terms of computation complexity and latency. Due to poor perception of spatial features, the accuracy of the existing single-stage anchor-free detection algorithms with low latency are difficult to be implemented into autonomous vehicles. Therefore, we focus on enhancing the spatial perception ability of the anchor-free detection network based on CenterPoints. In this paper, we propose a single-stage anchor-free 3-D object detector CenterPoint-Space-Enhancement (CenterPoint-SE) algorithm and construct an efficient 3-D backbone network to extract fine-grained spatial geometric features by introducing a spatial attention mechanism and residual structure. At the same time, a powerful spatial semantic feature fusion module, the enhancement of feature fusion (EF-Fusion), is designed. In addition, we add a lightweight IoU prediction branch to improve the algorithm’s perception of various object sizes. Finally, we add a foreground point segmentation auxiliary training branch to enable the 3-D backbone to obtain object boundary features. We use the ONCE dataset to train and validate the proposed model, and the results showed that the proposed CenterPoint-SE achieves 70.33 mAP and an inference speed of 17.15 FPS, outperforming other methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    CenterPoint-SE: A Single-Stage Anchor-Free 3-D Object Detection Algorithm With Spatial Awareness Enhancement


    Beteiligte:
    Wang, Hai (Autor:in) / Tao, Le (Autor:in) / Cai, Yingfeng (Autor:in) / Chen, Long (Autor:in) / Li, Yicheng (Autor:in) / Sotelo, Miguel Angel (Autor:in) / Li, Zhixiong (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.10.2023


    Format / Umfang :

    14666211 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Evaluation of Single-Stage, Two-Stage, and Anchor-Free Object Recognition Methods for UAV Detection

    Al Romaihi, Rashed Khamis / Belhi, Abdelhak / Hadjidj, Rachid | Springer Verlag | 2023


    Improved RepVGG-based Anchor-free Algorithm for On-road Object Detection

    Lian, Zheng / Nie, Yiming / Dai, Bin et al. | IEEE | 2022


    Analysis of Anchor-Based and Anchor-Free Object Detection Methods Based on Deep Learning

    Liu, Shujian / Zhou, Haibo / Li, Chenming et al. | British Library Conference Proceedings | 2020



    Vehicle Detection in Indian Traffic Using an Anchor-Free Object Detector

    Deshmukh, Prashant / Kadha, Vijayakumar / Rayasam, Krishna Chaitanya et al. | Springer Verlag | 2023