A point cloud segmentation method for power lines and towersbased on a combination of multiscale density features andpoint-based deep learning

作     者：Wenbo Zhao Qing Dong Zhengli Zuo 

作者机构：Key Laboratory of Digital Earth ScienceAerospace Information Research InstituteChinese Academy of SciencesBeijingPeople’s Republic of China International Research Center of Big Data for Sustainable Development GoalsBeijingPeople’s Republic of China University of Chinese Academy of SciencesBeijingPeople’s Republic of China Laboratory of Target Microwave PropertiesDeqing Academy of Satellite ApplicationsZhejiangPeople’s Republic of China 

出 版 物：《International Journal of Digital Earth》 (国际数字地球学报（英文）)

年 卷 期：2023年第16卷第1期

页      面：620-644页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 080203[工学-机械设计及理论] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Chengdu University of Technology Postgraduate Innovative Cultivation Program(CDUT2022BJCX015) 

主　　题：Power lines and power towers point cloud segmentation multiscale density features PointCNN 

摘      要：The point segmentation of power lines and towers aims to use unmanned aerial vehicles(UAVs)for the inspection of power facilities,risk detection and *** of the unclear spatial relationship between the point clouds,the point segmentation of power lines and towers is *** this paper,the power line and tower point datasets are constructed using Light Detection and Ranging(LiDAR)and a point segmentation method is proposed based on multiscale density features and a point-based deep learning ***,the data are blocked and the neighbourhood is ***,the point clouds are downsampled to produce sparse point *** point clouds before and after sampling are rotated,and their density is ***,a direct mapping method is selected to fuse the density information;a lightweight network is built to learn the ***,the point clouds are segmented by concatenating the local features provided by *** algorithm performs effectively on different types of power lines and *** mean interaction over union is 82.73%,and the overall accuracy can reach 91.76%.This approach can achieve the end-to-end integration of segmentation and provide theoretical support for the segmentation of large scenic point clouds.