您的位置：首页 > 论文页面
激光雷达点云配准技术研究
发表时间：2022-06-27 浏览量：1459 下载量：122
| 全部作者： | 周朝，乔耀军，杨爱英 |
| 作者单位： | 北京邮电大学信息与通信工程学院；北京理工大学光电学院 |
| 摘 要： | 激光雷达（LiDAR）是三维定位、导航、建图和自动驾驶领域的重要传感器，点云配准技术是对激光雷达点云数据进行处理时不可缺少的重要前序步骤。对激光雷达点云配准领域常用方法进行了研究，并按照不同的分类标准对其间的联系进行了比较和总结。将众多方法按照处理基元的不同划分为基于点基元、几何基元以及体素基元三类，对不同类别方法的基本原理和标准算法流程进行了提炼，对其中的部分重要模块进行了介绍和分析，并针对各类方法进行了优缺点分析和对比。最后，对点云配准算法开发中的重要问题——配准评价体系展开了深入分析，并对点云配准方法未来可能的改进方向进行了展望。 |
| 关 键 词： | 信息处理技术；激光雷达；综述；点云配准 |
| Title： | LiDAR point cloud registration technology |
| Author： | ZHOU Zhao, QIAO Yaojun, YANG Aiying |
| Organization： | School of Information and Communication Engineering, Beijing University of Posts and Telecommunications; School of Optics and Photonics, Beijing Institute of Technology |
| Abstract： | LiDAR is an important sensor in the fields of three-dimensional positioning, navigation, mapping and autonomous driving. Point cloud registration technology is an indispensable and important pre-step for processing point cloud data of LiDAR. In this paper, the common methods in the field of LiDAR point cloud registration are studied, and the relationships among them are compared and summarized with different classification standards. Subsequently, according to the different processing primitives, a lot of methods are divided into point primitives, geometric primitives and voxel primitives three families of method. The basic principles and standard algorithm procedures of different families of method are refined, part of the important modules are introduced and analyzed, and the advantages and disadvantages of various methods are analyzed and compared. Finally, an important issue in the exploration of the point cloud registration algorithm, the registration evaluation system is analyzed in depth, and the possible future improvement directions of the point cloud registration method are prospected. |
| Key words： | information processing technology; LiDAR; review; point cloud registration |
| 发表期数： | 2022年6月第2期 |
| 引用格式： | 周朝，乔耀军，杨爱英. 激光雷达点云配准技术研究[J]. 中国科技论文在线精品论文，2022，15（2）：143-151. |
6
评论数 0请您登录
暂无评论
下载全文
多维论文