基于高斯混合优化的机载雷达点云单木分割研究  

Research on Single Tree Segmentation in Airborne LiDAR Point Cloud Based on Gaussian Mixture Optimization

作　　者：张坤祥 夏永华 侯云花 时盛春 鄢敏 沈长表 李雪[1] 无 Zhang Kunxiang;Xia Yonghua;Hou Yunhua;Shi Shengchun;Yan Min;Shen Changbiao;Li Xue;无(School of Geosciences and Surveying Engineering,Kunming University of Science and Technology,Kunming 650093,Yunnan,China;College of Urban,Kunming University of Science and Technology.Kunming 650051,Yunnan,China;Yunnan Provincial Key Laboratory of Geomatics in High-speed Railway,Kunming University of Science and Technology,Kunming 650093,Yunnan,China)

机构地区：[1]昆明理工大学国土资源工程学院,云南昆明650093 [2]昆明理工大学城市学院,云南昆明650051 [3]昆明理工大学云南高校高原山区空间信息测绘技术应用工程研究中心,云南昆明650093

出　　处：《应用激光》2025年第1期153-164,共12页Applied Laser

摘　　要：针对森林复杂空间导致的单木点云分割精度低的问题,以昆明市西山区海口林场的针叶林和落叶阔叶林两块样地作为研究对象,利用机载LiDAR点云数据,提出一种基于种子点优化的单木分割算法。该方法结合最远点采样和K近邻搜索方法探测单木的树顶点信息,使用K均值聚类实现种子点的优化选取,然后采用期望最大化算法寻求高斯混合模型的最优参数,提高高斯混合模型的拟合精度,最后,基于最优参数的高斯混合模型获取单木点云的分割结果。实验结果表明:研究提出的单木分割方法在两个实验样地的单木分割总精度O_(accu)分别为89.98%和90.43%,具有良好的单木分割效果,对林区树冠粘连和伪树冠顶点现象具有一定的辨别能力,实现了森林树木点云数据的精确分割。Addressing the issue of low accuracy in single tree segmentation of forest point clouds in complex spatial environments,this study focuses on two sample areas,namely coniferous and broad-leaved forests in Haikou Forest Farm,Xishan District,Kunming City.Utilizing airborne LiDAR point cloud data,a seed-based optimization algorithm is proposed for single tree segmentation.The method combines farthest point sampling and K-nearest neighbor search to identify tree top points,optimizes seed point selection through K-means clustering,and utilizes the Expectation-Maximization algorithm to determine the optimal parameters of a Gaussian Mixture Model,thereby improving its fitting accuracy.Finally,the single tree point cloud segmentation results are obtained based on the optimized Gaussian Mixture Model.Experimental results demonstrate the effectiveness of the proposed method,achieving overall accuracies O_(accu)(%)of 89.98%and 90.43%for the two study sites,respectively.The method exhibits good performance in accurately segmenting individual trees,distinguishing between connected tree crowns and pseudo-tree top points,and achieving precise segmentation of forest tree point cloud data.

关 键 词：机载激光雷达 种子点 单木分割 K均值聚类 高斯混合模型 

分 类 号：TN957.52[电子电信—信号与信息处理]