A review of deep learning based on 3D point cloud segmentation

被引：0
|
作者：
Lu J. [1 ]
Jia X.-R. [1 ]
Zhou J. [1 ]
Liu W. [1 ]
Zhang K.-B. [1 ]
Pang F.-F. [1 ]
机构：
[1] School of Electronics and Information, Xi'an Polytechnic University, Xi'an
来源：
Kongzhi yu Juece/Control and Decision | 2023年 / 38卷 / 03期
关键词：
3D point cloud; datasets; deep learning; instance segmentation; part segmentation; semantic segmentation;
D O I：
10.13195/j.kzyjc.2021.1648
中图分类号：
学科分类号：
摘要：
3D point cloud segmentation, as one of the important technology of 3D scene understanding, has aroused people's widespread interest. And it has important research value and broad application prospect. The latest research progress of 3D point cloud segmentation technology based on deep learning is sorted out. Firstly, eight indoor and outdoor common datasets frequently utilized in 3D point cloud segmentation are introduced. Then, the existing semantic segmentation, instance segmntation and part segmentation mainly via deep learning are explained and analyzed in depth, and the effectiveness of some methods is compared baesd on quantitative data. Finally, we summarize the shortcomings of the existing methods from ten aspects, and put forward the work prospects pertinently. © 2023 Northeast University. All rights reserved.
引用
收藏
页码：595 / 611
页数：16
相关论文
共 119 条
  • [1] Qi C R, Liu W, Wu C, Et al., Frustum PointNets for 3D object detection from RGB-D data, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 918-927, (2018)
  • [2] Park Y, Lepetit V, Woo W., Multiple 3D object tracking for augmented reality, The 7th IEEE/ACM International Symposium on Mixed and Augmented Reality, pp. 117-120, (2008)
  • [3] Xi X H, Wan Y P, Wang C., Building boundaries extraction from points cloud using an image edge detection method, 2016 IEEE International Geoscience and Remote Sensing Symposium, pp. 1270-1273, (2016)
  • [4] Ni H, Lin X G, Ning X, Et al., Edge detection and feature line tracing in 3D-point clouds by analyzing geometric properties of neighborhoods, Remote Sens, 8, (2016)
  • [5] Vo A V, Truong-Hong L, Laefer D F, Et al., Octree-based region growing for point cloud segmentation, ISPRS Journal of Photogrammetry and Remote Sensing, 104, pp. 88-100, (2015)
  • [6] Fan S N, Huang N, Fang P F, Et al., A 3D point cloud segmentation method based on local convexity and dimension features, 2018 Chinese Control and Decision Conference(CCDC), pp. 5012-5017, (2018)
  • [7] Klasing K, Wollherr D, Buss M., A clustering method for efficient segmentation of 3D laser data, IEEE International Conference on Robotics and Automation, pp. 4043-4048, (2008)
  • [8] Hao W, Wang Y, Ning X, Et al., Automatic building extraction from terrestrial laser scanning data, Advances in Electrical and Computer Engineering, 13, 3, pp. 11-16, (2013)
  • [9] Schnabel R, Wahl R, Klein R., Efficient RANSAC for point-cloud shape detection, Computer Graphics Forum, 26, 2, pp. 214-226, (2007)
  • [10] Wang Y M, Shi H B., A segmentation method for point cloud based on local sample and statistic inference, Geo-Informatics in Resource Management and Sustainable Ecosystem, pp. 274-282, (2014)
12345678910