顾及杆状物和车道线的城市道路场景轻量化快速点云自动配准  

Urban road scenes utilize lightweight fast point cloud auto-registration of poles-like and lane lines

作　　者：赵辉友 吴学群[1] 夏永华[1] ZHAO Huiyou;WU Xuequn;XIA Yonghua(College of Mechanical Engineering,Kunming University of Science and Technology,Kunming 600093,China)

机构地区：[1]昆明理工大学国土资源工程学院,云南昆明600093

出　　处：《光学精密工程》2024年第4期535-548,共14页Optics and Precision Engineering

基　　金：国家自然科学基金地区基金项目(No.42161067,No.42261074)。

摘　　要：针对激光扫描获取城市场景出现不同时期位置偏差,传统点云配准方法存在效率低和鲁棒性低等局限性,本文提出了顾及杆状物和车道线的点云配准改进方法。首先对滤波后的点云进行体素格网降采样,再利用布料模型滤波对地面点滤波,后使用K均值无监督分类非地面点云,后用先验的随机一致抽样法提取杆状物作为目标特征,并根据点云反射强度提出点云灰度图和空间密度分割法提取车道线。利用改进迭代最近点(ICP)算法和法向量约束,将杆状物作和车道线作为配准基元,几何一致算法剔除错误点对,并使用双向KD-tree快速对应特征点的关系,加快配准速度和提高精度。经实验证明,在低重叠度的城市点云场景耗时不到20 s,且只迭代20次,精度可达1.9877×10^(-5)m,可实现城市道路场景点云的高效准确配准。In view of the position deviation of vehicle laser scanning to obtain urban scenes in different peri⁃ods,the Traditional point cloud registration methods still have the limitations of low efficiency and low ro⁃bustness,and an improved point cloud registration method using rods and lane lines was proposed in this pa⁃per.Firstly,the filtered point cloud was voxel grid down-sampled,and then the cloth model was used to fil⁃ter the ground points,and then the K-means unsupervised classification of non-ground point clouds was used,and then the rods were extracted as the target features,and the point cloud grayscale map and spatial density segmentation method were proposed according to the reflection intensity of the point cloud.Then,the improved iterative closest point(ICP)algorithm and normal constraint were used to use rods and lane lines as registration primitives,geometric consistency algorithms were used to eliminate wrong point pairs,and bidirectional KD-trees were used to quickly correspond to the relationship of feature points,so as to accelerate the registration speed and improve accuracy.Experiments show that it takes less than 20 s in urban point cloud scenarios with low overlap,and only 20 iterations,and the accuracy can reach 1.9877×10^(-5)me⁃ters,which can realize the efficient and accurate registration of laser point clouds in urban road scenes.

关 键 词：车载激光扫描 杆状物 地面点滤波 K均值 车道线 改进ICP 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术] TH691.9[自动化与计算机技术—计算机科学与技术]