Journal of Frontiers of Computer Science and Technology ›› 2022, Vol. 16 ›› Issue (12): 2695-2717.DOI: 10.3778/j.issn.1673-9418.2206026

• Surveys and Frontiers • Previous Articles     Next Articles

Research Progress on 3D Object Detection of LiDAR Point Cloud

ZHOU Yan, PU Lei(), LIN Liangxi, LIU Xiangyu, ZENG Fanzhi, ZHOU Yuexia   

  1. Department of Computer Science, Foshan University, Foshan, Guangdong 528000, China
  • Received:2022-06-06 Revised:2022-08-31 Online:2022-12-01 Published:2022-12-16
  • About author:ZHOU Yan, born in 1979, M.S., professor, M.S. supervisor, member of CCF. Her research inte-rests include image processing, computer vision and machine learning.
    PU Lei, born in 1998, M.S. candidate. His re-search interests include computer vision and 3D object detection.
    LIN Liangxi, born in 1995, M.S. candidate. His research interests include computer vision and 3D object detection.
    LIU Xiangyu, born in 1987, Ph.D., lecturer, member of CCF. Her research interests include computer vision, machine learning and human-computer interaction.
    ZENG Fanzhi, born in 1965, Ph.D., professor, M.S. supervisor, member of CCF. His research interests include computer vision, image proces-sing and data mining.
    ZHOU Yuexia, born in 1978, M.S., lecturer. Her research interest is information acquisition and processing.
  • Supported by:
    National Natural Science Foundation of China(61972091);Natural Science Foundation of Guangdong Province(2022A1515010101);Natural Science Foundation of Guangdong Province(2021A1515012639);Key Research Project of University of Guangdong Province(2019KZDXM007);Key Research Project of University of Guangdong Province(2020ZDZX3049);Science and Technology Innovation Project of Foshan(2020001003285);Educational Science Planning Project of Guangdong Province(2021GXJK445)


周燕, 蒲磊(), 林良熙, 刘翔宇, 曾凡智, 周月霞   

  1. 佛山科学技术学院 计算机系,广东 佛山 528000
  • 通讯作者: +E-mail:
  • 作者简介:周燕(1979—),女,江西抚州人,硕士,教授,硕士生导师,CCF会员,主要研究方向为图像处理、计算机视觉、机器学习。
  • 基金资助:


3D object detection is a new research direction in recent years, and its main task is the location and recognization of targets in space. The existing methods for 3D object detection using monocular or binocular stereo vision are easily affected by object occlusion, viewpoint changing and scale changing in 3D scene, there will be problems such as poor detection accuracy and robustness. LiDAR point cloud can provide 3D scene information, so using deep learning method to complete 3D object detection based on LiDAR point cloud has become a research hotspot in the field of 3D vision. Aiming at the 3D object detection based on LiDAR point cloud, the relevant research in recent years is reviewed. Firstly, the 3D object detection methods based on LiDAR point cloud are divided into point cloud based, point cloud projection based, point cloud voxelization based and multi-modal fusion based 3D object detection methods according to the data form of network input, and the most representative methods in each category are described in detail. Then common datasets are introduced, and the performance of representative methods is evaluated, and the advantages and limitations of each method are discussed from several aspects. Finally, the shortcomings and difficulties are given, and the future development directions are also discussed and put forward.

Key words: 3D object detection, LiDAR point cloud, deep learning



关键词: 三维目标检测, 激光点云, 深度学习

CLC Number: