改进高斯混合模型的激光点云数据分类  

Classification of laser point cloud data based on Improved Gaussian mixture model

作　　者：张忠琼[1] 赵颖[1] 钱淑渠[1] ZHANG Zhongqiong;ZHAO Ying;QIAN Shuqu(Anshun University,School of mathematics and computer science,Anshun Guizhou 561000,China)

机构地区：[1]安顺学院数学与计算机科学学院,贵州安顺561000

出　　处：《激光杂志》2023年第6期215-219,共5页Laser Journal

基　　金：贵州省教育厅创新群体重大项目资助(No.黔教合KY字[2019]069,[2018]034)。

摘　　要：激光点云数据的无序性会影响激光场景识别和三维重建,导致激光点云数据分类误差大,精度低等问题,为此提出基于改进高斯混合模型的激光点云数据分类方法。首先采集激光点云数据,利用邻域密度算法对数据中的噪声进行分析和去除,然后采用改进高斯混合模型获取数据点间距,将点云数据分类相应类别中,实现激光点云数据分类。实验结果证明,本方法可以有效去除激光点云数据中的孤立点,提高了激光点云数据分类精度,激光点云数据分类结果可满足激光三维重建要求。The disorder of laser point cloud data will affect laser scene recognition and 3D reconstruction,resulting in large classification errors and low accuracy of laser point cloud data.Therefore,a laser point cloud data classification method based on improved Gaussian mixture model is proposed.First,the laser point cloud data is collected,and the noise in the data is analyzed and removed by using the neighborhood density algorithm.Then,the improved Gaussian mixture model is used to obtain the data point spacing,and the point cloud data is classified into the corresponding categories to realize the laser point cloud data classification.The experimental results show that the method in this paper can effectively remove the isolated points in the laser point cloud data,improve the classification accuracy of the laser point cloud data,and the classification results of the laser point cloud data can meet the requirements of laser 3D reconstruction.

关 键 词：高斯混合模型 激光点云 数据分类 邻域密度 

分 类 号：TN341[电子电信—物理电子学]