计算机科学与探索 ›› 2021, Vol. 15 ›› Issue (1): 1-26.DOI: 10.3778/j.issn.1673-9418.2006025

• 综述·探索 • 上一篇    下一篇

基于深度学习的点云语义分割研究综述

景庄伟,管海燕,臧玉府,倪欢,李迪龙,于永涛   

  1. 1. 南京信息工程大学 地理科学学院,南京 210044
    2. 南京信息工程大学 遥感与测绘工程学院,南京 210044
    3. 武汉大学 测绘遥感信息工程国家重点实验室,武汉 430079
    4. 淮阴工学院 计算机与软件学院,江苏 淮安 223003
  • 出版日期:2021-01-01 发布日期:2021-01-07

Survey of Point Cloud Semantic Segmentation Based on Deep Learning

JING Zhuangwei, GUAN Haiyan, ZANG Yufu, NI Huan, LI Dilong, YU Yongtao   

  1. 1. School of Geographical Science, Nanjing University of Information Science & Technology, Nanjing 210044, China
    2. School of Remote Sensing & Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China
    3. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
    4. Faculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huai'an, Jiangsu 223003, China
  • Online:2021-01-01 Published:2021-01-07

摘要:

近年来,深度传感器和三维激光扫描仪的普及推动了三维点云处理方法的快速发展。点云语义分割作为理解三维场景的关键步骤,受到了研究者的广泛关注。随着深度学习的迅速发展并广泛应用到三维语义分割领域,点云语义分割效果得到了显著提升。主要对基于深度学习的点云语义分割方法和研究现状进行了详细的综述。将基于深度学习的点云语义分割方法分为间接语义分割方法和直接语义分割方法,根据各方法的研究内容进一步细分,对每类方法中代表性算法进行分析介绍,总结每类方法的基本思想和优缺点,并系统地阐述了深度学习对语义分割领域的贡献。然后,归纳了当前主流的公共数据集和遥感数据集,并在此基础上对比主流点云语义分割方法的实验结果。最后,对语义分割技术未来的发展方向进行了展望。

关键词: 深度学习, 语义分割, 点云, 计算机视觉

Abstract:

In recent years, the popularity of depth sensors and 3D laserscanners has led to a rapid development of 3D point clouds processing methods. Semantic segmentation of point cloud, as a key step in understanding 3D scenes, has attracted extensive attention of researchers. With the rapid development of deep learning and its widespread applications in 3D semantic segmentation, the quality of point cloud semantic segmentation has been significantly improved. This paper mainly reviews the deep learning-based point cloud semantic segmentation methods and their research status. This paper categories these deep learning-based methods for point clouds into two groups: indirect and direct semantic segmentation methods. In terms of the characteristics of the algorithm, each of groups is  further subdivided. The representative algorithms are analyzed and introduced. This paper summarizes the theories, principles, advantages and disadvantages of each type of method, and systematically explains the contribution of deep learning to the field of semantic segmentation. Moreover, the current mainstream datasets and remote sensing datasets are summarized and the experimental results of some algorithms are compared. Finally, the future development direction of semantic segmentation technology is prospected.

Key words: deep learning, semantic segmentation, point cloud, computer vision