摘要
针对移动车载激光扫描点云数据中杆状物分类精度不理想的问题,本文从杆状物的空间形态特征出发,构建一种基于支持向量机(SVM)模型的杆状物分类算法。首先,根据杆状物空间形态特征确定10个特征值并建立特征矩阵;其次,进行SVM模型训练并建立分类模型;最后,使用训练好的最优SVM模型进行杆状物分类。选取某段城市道路的点云数据进行试验,结果表明,本文分类模型无须人工干预与阈值设定,自动化程度高,其中杆状物的最高分类精度能够达到94.23%。该算法具有有效性与优越性,可为基于激光点云数据的地物分类提供一定借鉴与参考。
In response to the problem of unsatisfactory classification accuracy of rods in mobile vehicle-mounted laser scanning point cloud data,this paper constructed a rod classification algorithm based on the support vector machine(SVM) model regarding the spatial morphology characteristics of rods.Firstly,10 feature values were determined,and a feature matrix was established based on the spatial morphology characteristics of the rods.Secondly,the SVM model was trained,and a classification model was established.Finally,the trained optimal SVM model was used for rod classification.A certain section of urban road point cloud data was selected for testing,and the results show that the classification model in this paper does not require manual intervention and threshold setting,and it has a high degree of automation.Its highest classification accuracy of rods can reach 94.23%,verifying its effectiveness and superiority.It can provide some reference for ground object classification based on laser point cloud data.
作者
朱丹
ZHU Dan(Taiyuan Institute of Land and Space Planning and Surveying(Taiyuan Urban Sculpture Research Institute),Taiyuan,Shanxi 030002,China)
出处
《北京测绘》
2024年第6期880-885,共6页
Beijing Surveying and Mapping
关键词
车载激光扫描
点云
杆状物
支持向量机(SVM)
特征值
vehicle-mounted laser scanning
point cloud
rod
support vector machine(SVM)
feature value
