检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:殷建政 张闪 叶送 YIN Jianzheng;ZHANG Shan;YE Song(Zhejiang Provincial Institute of Surveying and Mapping Science and Technology,Hangzhou 311100,China)
机构地区:[1]浙江省测绘科学技术研究院,浙江杭州311100
出 处:《测绘与空间地理信息》2024年第11期205-207,211,共4页Geomatics & Spatial Information Technology
摘 要:为了提高基于机载LiDAR点云数据的道路标识线分类精度,提高机载LiDAR点云数据的利用率,本文提出了一种从机载LiDAR点云数据中自动提取道路标识线的新方法。该新方法实现道路标识线自动提取的步骤为:首先,对原始机载LiDAR点云数据进行滤波处理,消除地物点对道路标识线点云提取的影响;其次,对道路面点云数据进行二维投影,获取道路点云数据的强度特征图,并根据标识线连通分析得到标识线边缘信息;最后,通过指定约束识别规则实现道路标识线的精细化处理。使用两组机载LiDAR点数据进行实验,结果表明,本文提出的新方法能够很好地获取道路标识线边缘与标识线点云,提取道路标识线的平均完整率与平均正确率分别为0.94、0.98,均优于对比方法实验结果,具有实用性强、鲁棒性好的特点。In order to improve the classification accuracy of road marking lines based on airborne LiDAR point cloud data and improve the utilization rate of airborne LiDAR point cloud data,this paper proposes a new method to automatically extract road marking lines from airborne LiDAR point cloud data.The steps of the new method to realize automatic extraction of road marking lines are as follows:Firstly,we filter the original airborne LiDAR point cloud data to eliminate the impact of ground object points on road marking line point cloud extraction;Secondly,2D projection of road surface point cloud data is carried out to obtain the intensity feature map of road point cloud data,and the edge information of the marking line is obtained according to the connectivity analysis of the marking line;Finally,road marking lines are refined by specifying constraint recognition rules.Two sets of airborne LiDAR point data are used for experiments.The results show that the new method proposed in this paper can well obtain the edge and point cloud of road marking lines,and the average integrality and accuracy of road marking lines are 0.94 and 0.98 respectively,which are better than the experimental results of the comparative method and have the characteristics of strong practicality and robustness.
关 键 词:机载LiDAR点云数据 强度特征图像 边缘检测 标识线提取
分 类 号:P25[天文地球—测绘科学与技术] TN958.98[电子电信—信号与信息处理]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:3.137.210.169