Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage 3D object detection methods can achieve real-time performance, however, they are dominated by anchor-based detectors which are inefficient and require additional post-processing. In this paper, we eliminate anchors and model an object as a single point—the center point of its bounding box. Based on the center point, we propose an anchor-free CenterNet3D network that performs 3D object detection without anchors. Our CenterNet3D uses keypoint estimation to find center points and directly regresses 3D bounding boxes. However, because inherent sparsity of point clouds, 3D object center points are likely to be in empty space which makes it difficult to estimate accurate boundaries. To solve this issue, we propose an extra corner attention module to enforce the CNN backbone to pay more attention to object boundaries. Besides, considering that one-stage detectors suffer from the discordance between the predicted bounding boxes and corresponding classification confidences, we develop an efficient keypoint-sensitive warping operation to align the confidences to the predicted bounding boxes. Our proposed CenterNet3D is non-maximum suppression free which makes it more efficient and simpler. We evaluate CenterNet3D on the widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art anchor-based one-stage methods and has comparable performance to two-stage methods as well. It has an inference speed of 20 FPS and achieves the best speed and accuracy trade-off. Our source code will be released at https://github.com/wangguojun2018/CenterNet3d.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    CenterNet3D: An Anchor Free Object Detector for Point Cloud


    Contributors:
    Wang, Guojun (author) / Wu, Jian (author) / Tian, Bin (author) / Teng, Siyu (author) / Chen, Long (author) / Cao, Dongpu (author)


    Publication date :

    2022-08-01


    Size :

    4191536 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    ElDet: An Anchor-Free General Ellipse Object Detector

    Wang, Tianhao / Lu, Changsheng / Shao, Ming et al. | British Library Conference Proceedings | 2023


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

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



    ANCHOR POINT

    PETERSSON THOMAS | European Patent Office | 2019

    Free access

    ANCHOR POINT

    European Patent Office | 2017

    Free access