基于车载激光点云的城市道路标线提取方法  

Urban road marking extraction method based on vehicle laser point cloud

作　　者：周松 刘荣[1,2] 陈志高[1,2] 段炬奎 ZHOU Song;LIU Rong;CHEN Zhi-gao;DUAN Ju-kui(School of Surveying and Geoinformation Engineering,East China University of Technology,Nanchang 330013,China;Key Laboratory of Mine Environmental Monitoring and Improving around Poyang Lake of Ministry of Natural Resources,East China University of Technology,Nanchang 330013,China;No.209 Geological Party,Geological Bureau of Yunnan Nuclear Industry,Kunming 650092,China)

机构地区：[1]东华理工大学测绘与空间信息工程学院,江西南昌330013 [2]东华理工大学自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室,江西南昌330013 [3]云南省核工业二〇九地质大队,云南昆明650092

出　　处：《激光与红外》2024年第3期396-403,共8页Laser & Infrared

基　　金：国家自然科学基金项目(No.42266006,No.41806114)资助。

摘　　要：针对车载激光点云道路标线反射强度特性,提出了一种基于车载激光点云的城市道路标线提取方法。具体而言,首先提出一种联合布料模拟滤波和高差偏度平衡的地面滤波方法,利用偏度平衡滤波的自适应性,剔除布料滤波后残留的低矮植被的问题;随后利用基于法向量密度聚类以提取路面点云,并通过反距离加权插值将路面点云转为强度特征图;为了缓解标线提取出的锯齿状现象,引入快速引导滤波来平滑道路标线的边缘信息;最后采用最大熵阈值分割和形态学比值滤波对道路标线进行精化处理。实验表明,该方法能够有效地提取出道路标线点云,提取的平均召回率为80.98%,平均准确率为96.89%,平均综合评定指标为88.19%,能够利用道路标线点云强度信息较为完整地提取出道路标线点云。Aiming at the reflection intensity characteristics of road markings from vehicle mounted laser point cloud,an urban road marking extraction method based on vehicle laser point cloud is proposed.Firstly,a ground filtering method combining cloth simulation filtering and elevation skewness balance is presented to take advantage of the adaptability of skewness balance filtering to eliminate the problem of low vegetation remaining after cloth filtering.Then,the normal vector density clustering is adopted to extract the road point cloud,and the road point cloud is converted into an intensity feature map by inverse distance weighted interpolation.In order to alleviate the jaggedness extracted from the markers,fast bootstrap filtering is introduced to smooth the edge information of the road markers.Finally,the maximum entropy threshold segmentation and morphological ratio filtering are used to refine the road marker.The experimental results show that the method can effectively extract the road marking point cloud,the average recall rate of extraction is 80.98%,the average accuracy rate is 96.89%,and the average comprehensive evaluation index is 88.19%and it can use the road marking point cloud intensity information to extract the road marking point cloud in a more complete way.

关 键 词：点云 布料模拟 偏度平衡 反距离加权插值 快速引导滤波 

分 类 号：TN958.98[电子电信—信号与信息处理] TP391.14[电子电信—信息与通信工程]