露天铜矿爆堆三维激光点云超体素分割方法  

Application of 3D Laser Point Cloud Supervoxel Segmentation Method in the Muck Piles of Open Pit Copper Mine

作　　者：谢民民 XIE Minmin(School of Civil and Surveying&Mapping Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,China)

机构地区：[1]江西理工大学土木与测绘工程学院,江西赣州341000

出　　处：《测绘与空间地理信息》2025年第2期38-41,共4页Geomatics & Spatial Information Technology

基　　金：江西省研究生创新专项资金项目(YC2021-S561)资助。

摘　　要：目前,大多数露天铜矿的开采过程中都是基于二维图像系统进行爆堆矿石的识别,但是这种方法存在着诸多弊端。为了获取更高精度的爆堆矿石识别结果,本文利用三维激光扫描技术对爆堆进行扫描,得到爆堆的三维点云数据。然后,将基于超体素的点云分割方法应用到爆堆矿石的识别当中。同时,本文还将基于超体素的点云分割方法与几种常用点云分割方法进行对比实验,分别从定性定量的角度比较几种点云分割算法的矿石识别准确度。实验发现,基于超体素的CPC分割方法在爆堆矿石识别中的效果较好,能够为点云分割技术在爆堆矿石识别领域的应用提供一定的参考,同时也为爆堆块度计算、爆堆形态模拟预测等爆堆相关领域的研究提供了数据支撑。At present,the identification of the muck pile ores in many open pit copper mines is based on two-dimensional image system,but this method has many shortcomings.In order to improve the accuracy of identification results of the muck pile ores,three-dimensional laser scanning is used to scan the muck piles and obtain their three-dimensional point cloud data in this paper.Then,the point cloud segmentation method based on supervoxel is applied to the identification of the muck pile ores.At the same time,this paper also compares the point cloud segmentation method based on supervoxel with several common point cloud segmentation methods.The accuracy of ore identification of several point cloud segmentation algorithms is compared from qualitative and quantitative perspectives.The experimental results show that the point cloud segmentation method based on supervoxel(CPC)has a good effect in the identification of muck pile ores,which can provide a certain reference for the application of point cloud segmentation technologies in the field of muck pile ore identification.In addition,the experiment also provides data support for the research of the muck pile related fields such as muck pile lumpiness calculation and muck pile morphology simulation and prediction.

关 键 词：三维激光点云 矿山测量 欧式聚类 区域生长 LCCP CPC 

分 类 号：P231[天文地球—摄影测量与遥感]