Research progress of 3D point cloud analysis methods based on deep learning

被引：0
|
作者：
Chen H. [1 ]
Wu Y. [1 ]
Zhang Y. [1 ]
机构：
[1] College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing
来源：
Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | 2023年 / 44卷 / 11期
关键词：
3D point cloud analysis; classification and segmentation; deep learning; object detection; point cloud registration; point cloud stitching;
D O I：
10.19650/j.cnki.cjsi.J2311134
中图分类号：
学科分类号：
摘要：
Point cloud is the most commonly used form of 3D data processing in the fields of autonomous driving, robotics, remote sensing, augmented reality (AR), virtual reality (VR), electric power, architecture, etc. Deep learning methods can not only handle large-scale data, but also extract features independently. Therefore, point cloud deep learning methods have gradually become a research hotspot. This article reviews the research progress of 3D point cloud analysis methods based on deep learning in the past decade. Firstly, the relevant concepts of deep learning for 3D point cloud are presented. Then, for the four tasks of point cloud object detection and tracking, classification and segmentation, registration and matching, and stitching, the principles of the corresponding deep learning methods are elaborated. Their advantages and disadvantages are analyzed and compared. Next, eighteen kinds of point cloud datasets and performance evaluation indexes for four types of point cloud analysis tasks are introduced. The performance comparison results are given. Finally, the existing problems of point cloud analysis methods are pointed out, and the further research work is prospected. © 2023 Science Press. All rights reserved.
引用
收藏
页码：130 / 158
页数：28
相关论文
共 173 条
  • [1] GUO Y, BENNAMOUN M, SOHEL F, Et al., 3D object recognition in cluttered scenes with local surface features: A survey, IEEE Transactions on Pattern Analysis and Machine Intelligence, 36, 11, pp. 2270-2287, (2014)
  • [2] ZHENG SH W, LI W H, HU J Y., Vehicle detection in the traffic environment based on the fusion of laser point cloud and image information, Chinese Journal of Scientific Instrument, 40, 12, pp. 143-151, (2019)
  • [3] YU H SH, FU Q, SUN J, Et al., Improved 3D-NDT point cloud registration algorithm for indoor mobile robot, Chinese Journal of Scientific Instrument, 40, 9, pp. 151-161, (2019)
  • [4] ESPINOSA N, LENZ A, GROSS W, Et al., Towards fast 3D reconstruction of urban areas from aerial nadir images for a near real-time remote sensing system, IGARSS 2018—2018 IEEE International Geoscience and Remote Sensing Symposium, pp. 6472-6475, (2018)
  • [5] LIU W, LAI B, WANG C, Et al., Learning to match 2D images and 3D LiDAR point clouds for outdoor augmented reality, 2020 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), pp. 654-655, (2020)
  • [6] WIRTH F, QUEHL J, OTA J, Et al., PointAtMe: Efficient 3D point cloud labeling in virtual reality, 2019 IEEE Intelligent Vehicles Symposium, pp. 1693-1698, (2019)
  • [7] CHU T., Research and application on repairing method of terracotta warriors amy based on multi-scale point clouds and surface texture features, (2021)
  • [8] SI L, TAN CH, ZHU J H, Et al., A coal-gangue recognition method based on X-ray image and laser point cloud, Chinese Journal of Scientific Instrument, 43, 9, pp. 193-205, (2022)
  • [9] HOSOKI D, LU H, KIM H, Et al., Detection of facial symmetric plane based on registration of 3D point cloud, 2019 19th International Conference on Control, Automation and Systems (ICCAS), pp. 1037-1041, (2019)
  • [10] CHEN CH, MAI X M, SONG SH, Et al., Automatic power lines extraction method from airborne LiDAR point cloud, Geomatics and Information Science of Wuhan University, 40, 12, pp. 1600-1605, (2015)
12345678910