IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v11y2023i23p4809-d1289837.html
   My bibliography  Save this article

Point-Rich: Enriching Sparse Light Detection and Ranging Point Clouds for Accurate Three-Dimensional Object Detection

Author

Listed:
  • Yanchao Zhang

    (Special Equipment Safety Supervision Inspection Institute of Jiangsu Province, Nanjing 210036, China)

  • Yinuo Zheng

    (School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210001, China)

  • Dingkun Zhu

    (School of Computer Engineering, Jiangsu University of Technology, Changzhou 213001, China)

  • Qiaoyun Wu

    (School of Artificial Intelligence, Anhui University, Hefei 230601, China)

  • Hansheng Zeng

    (Special Equipment Safety Supervision Inspection Institute of Jiangsu Province, Nanjing 210036, China)

  • Lipeng Gu

    (School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210001, China)

  • Xiangping Bryce Zhai

    (School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210001, China)

Abstract

LiDAR point clouds often suffer from sparsity and uneven distributions in outdoor scenes, leading to the poor performance of cutting-edge 3D object detectors. In this paper, we propose Point-Rich, which is designed to improve the performance of 3D object detection. Point-Rich consists of two key modules: HighDensity and HighLight. The HighDensity module addresses the issue of density imbalance by enhancing the point cloud density. The HighLight module leverages image semantic features to enrich the point clouds. Importantly, Point-Rich imposes no restrictions on the 3D object detection architecture and remains unaffected by feature or depth blur. The experimental results show that compared with the Pointpillars on the KITTI dataset, the mAP of Point-Rich under the bird’s eyes view improves by 5.53% on average.

Suggested Citation

  • Yanchao Zhang & Yinuo Zheng & Dingkun Zhu & Qiaoyun Wu & Hansheng Zeng & Lipeng Gu & Xiangping Bryce Zhai, 2023. "Point-Rich: Enriching Sparse Light Detection and Ranging Point Clouds for Accurate Three-Dimensional Object Detection," Mathematics, MDPI, vol. 11(23), pages 1-11, November.
    • Handle: RePEc:gam:jmathe:v:11:y:2023:i:23:p:4809-:d:1289837
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/11/23/4809/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2227-7390/11/23/4809/
    Download Restriction: no
    ---><---

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jmathe:v:11:y:2023:i:23:p:4809-:d:1289837. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.