测绘学报 ›› 2019, Vol. 48 ›› Issue (12): 1575-1585.doi: 10.11947/j.AGCS.2019.20190465

• 综述 • 上一篇    下一篇

点云智能研究进展与趋势

杨必胜1,2, 董震1,2   

  1. 1. 武汉大学测绘遥感信息工程国家重点实验室, 湖北 武汉 430079;
    2. 时空数据智能获取技术与应用教育部工程研究中心, 湖北 武汉 430079
  • 收稿日期:2019-11-07 修回日期:2019-11-19 发布日期:2019-12-24
  • 作者简介:杨必胜(1974-),男,国家杰出青年科学基金获得者,长江学者特聘教授,博士生导师,主要从事无人机摄影测量与三维重建、点云智能处理、空间智能、GIS应用等方面的研究工作。E-mail:bshyang@whu.edu.cn
  • 基金资助:
    国家杰出青年科学基金(41725005);国家自然科学基金重点(41531177);教育部长江学者特聘教授奖励计划

Progress and perspective of point cloud intelligence

YANG Bisheng1,2, DONG Zhen1,2   

  1. 1. State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
    2. Engineering Research Center for Spatio-temporal Data Smart Acquisition and Application, Ministry of Education of China, Wuhan University, Wuhan 430079, China
  • Received:2019-11-07 Revised:2019-11-19 Published:2019-12-24
  • Supported by:
    The National Natural Science Foundation of China for Distinguished Young Scholars (No. 41725005);The Key Project of the National Natural Science Foundation of China (No. 41531177);The Yangtze River Scholar Distinguished Professor Program

摘要: 随着以激光扫描、倾斜摄影为主的各种现实采集(reality capture)装备的快速发展,点云已成为继矢量地图和影像数据之后的第三类重要的时空数据源,并在地球科学、空间认知、智慧城市等科学研究和工程建设中发挥越来越重要的作用。如何从点云大数据中快速、准确获取精准有效的三维地理信息成为测绘地理信息领域的科学前沿和地学应用研究的迫切需求,也是三维地理信息获取与建模面临的重大难题。点云智能应运而生,并成为突破上述难题的科学途径。本文围绕点云智能中的三个重要方向:点云大数据处理的理论方法,点云大数据智能处理关键技术和重大工程应用,阐述点云采集装备、智能化处理,以及科学研究与工程应用的最新进展,最后对点云智能的重要发展方向趋势予以展望,希望为点云研究相关人员提供科学参考。

关键词: 点云大数据, 点云智能, 语义标识, 结构化建模, 深度学习, 广义点云

Abstract: With the rapid development of the reality capture, such as laser scanning and oblique photogrammetry, point cloud has become the third important data source following vector maps and imagery, and also plays an increasingly important role in scientific research and engineering in the fields of earth science, spatial cognition, and smart city, and so on. However, how to acquire valid and accurate three-dimensional geospatial information from point clouds has become the scientific frontier and the urgent demand in the field of surveying and mapping as well as the geoscience applications. To address the challenges mentioned above, point cloud intelligence came into being. This paper summarizes the state-of-the art of point cloud intelligence in acquisition equipment, the intelligent processing, scientific research and the major engineering applications, focusing on its three important areas:the theoretical methods, the key techniques of intelligent processing and the major engineering applications. Finally, the promising development tendency of the point cloud intelligence is summarized.

Key words: point cloud big data, point cloud intelligence, semantic labeling, structured modelling, deep learning, ubiquitous point cloud

中图分类号: