多尺度邻域特征下的机载LiDAR点云电力线分类

doi:10.13474/j.cnki.11-2246.2019.0106

测绘通报 ›› 2019, Vol. 0 ›› Issue (4): 21-25.doi: 10.13474/j.cnki.11-2246.2019.0106

多尺度邻域特征下的机载LiDAR点云电力线分类

王艳军^1,2, 李凯^1,2, 路立娟³

1. 湖南科技大学地理空间信息技术国家地方联合工程实验室, 湖南湘潭 411201;
2. 湖南科技大学资源环境与安全工程学院, 湖南湘潭 411201;
3. 湘潭市国土资源信息中心, 湖南湘潭 411201

收稿日期:2018-07-23 修回日期:2018-09-07 出版日期:2019-04-25 发布日期:2019-05-07
作者简介:王艳军(1984-),男,博士,副教授,主要从事激光雷达点云数据处理与建模研究。E-mail:wongyanjun@163.com
基金资助:
国家自然科学基金（41601426；41771462）；湖南省自然科学基金（2018JJ3155）；数字制图与国土信息应用工程国家测绘地理信息局重点实验室开放基金（GCWD201806）

Power line classification from airborne LiDAR data via multi-scale neighborhood features

WANG Yanjun^1,2, LI Kai^1,2, LU Lijuan³

1. National-local Joint Engineering Laboratory of Geo-spatial Information Technology, Hunan University of Science and Technology, Xiangtan 411201, China;
2. School of Resource Environment and Safety Engineering, Hunan University of Science and Technology, Xiangtan 411201, China;
3. Xiangtan Land and Resources Information Center, Xiangtan 411201, China

Received:2018-07-23 Revised:2018-09-07 Online:2019-04-25 Published:2019-05-07

摘要/Abstract

摘要：

利用机载激光雷达技术三维测量精度高且获取快速的优点进行电力线自动分类提取已成为点云数据处理与电力应用的重要领域。针对电力线分类模型的自动化和高精度需求，本文提出了基于三维多尺度邻域特征的机载LiDAR点云电力线分类提取模型框架，主要包括4个步骤：电力线候选点滤波、多尺度邻域类型选取、形状结构特征提取和支持向量机分类。通过对2个复杂城市区域的试验数据集和8种不同邻域类型的详细结果对比分析，发现基于多尺度圆球邻域形状结构特征的分类模型结果准确率、召回率和质量分别达到97%、94%和93%，同时整体处理时间在2个试验数据中分别从366、256 s减少到274、160 s。试验结果表明，该方法在多种复杂城市场景中能够实现机载LiDAR数据的电力线较高精度分类提取。

关键词: 机载激光雷达, 城区电力线, 邻域选取, 形状结构特征, 电力线分类

Abstract:

With the rapid development of 3D accurate measurement technology of airborne LiDAR, automatic extraction of power lines from airborne laser point clouds has become an important topic in point cloud data processing and transmission line management. In this paper, we present an automated and versatile framework for power line classification, which consists of four steps:power line candidate point filtering, multi-scale neighborhood type selection, feature extraction based on geospatial structure, and SVM classification. To comprehensively evaluate the proposed algorithm, we calculate each point's feature based on eight levels of scales. Two datasets demonstrate that classification results reach up to 97%, 94%, and 93% in terms of precision rate, recall rate and overall quality. The whole processing time also decreases from 366 s, 256 s to 274 s, 160 s, respectively. Experimental results show that this method can achieve high-precision classification of power lines in complex urban environment.

Key words: airborne LiDAR, urban power line, neighborhood selection, geospatial structure feature, power line classification

中图分类号:

P234.4

王艳军, 李凯, 路立娟. 多尺度邻域特征下的机载LiDAR点云电力线分类[J]. 测绘通报, 2019, 0(4): 21-25.

WANG Yanjun, LI Kai, LU Lijuan. Power line classification from airborne LiDAR data via multi-scale neighborhood features[J]. 测绘通报, 2019, 0(4): 21-25.

参考文献

[1] AHMAD J, MALIK A S, XIA L, et al. Vegetation encroach-ment monitoring for transmission lines right-of-ways:a survey[J]. Electric Power Systems Research, 2013, 95:339-352.
[2] MCMANAMON P F. Review of ladar a historic, yet emer-ging, sensor technology with rich phenomenology[J]. Optical Engineering, 2012,51(6):60901-60913.
[3] 张昌赛, 许志海, 杨树文, 等. 机载LiDAR辅助下的电力线路弧垂分析及应用[J]. 测绘通报, 2017(7):94-98.
[4] CHENG L, TONG L, WANG Y, et al. Extraction of urban power lines from vehicle-borne LiDAR data[J]. Remote Sensing, 2014,6(4):3302-3320.
[5] ZHU L, HYYPPA J. Fully-automated power line extraction from airborne laser scanning point clouds in forest areas[J]. Remote Sensing, 2014, 6(11):11267-11282.
[6] GUAN H, YU Y, LI J, et al. Extraction of power-transmission lines from vehicle-borne lidar data[J]. International Journal of Remote Sensing, 2016, 37(1):229-247.
[7] 林祥国,张继贤. 架空输电线路机载激光雷达点云电力线三维重建[J]. 测绘学报,2016,45(3):347-353.
[8] GRIGILLO D, QZVALDIC S, VRECKO A, et al. Extraction of power lines from airborne and terrestrial laser scanning data using the hough transform[J]. Geodetski Vestnik, 2015, 59(2):246-261.
[9] KIM H B, SOHN G. Point-based classification of power line corridor scene using random forests[J]. Photogram-metric Engineering & Remote Sensing, 2013, 79(9):821-833.
[10] GUO B, LI Q, HUANG X, et al. An improved method for power-line reconstruction from point cloud data[J]. Remote Sensing, 2016, 8(1):36.
[11] 杨必胜,董震,魏征,等. 从车载激光扫描数据中提取复杂建筑物立面的方法[J]. 测绘学报,2013,42(3):411-417.
[12] JWA Y, SOHN G. A piecewise catenary curve model growing for 3D power line reconstruction[J]. Photogrammetric Engineering & Remote Sensing, 2012, 78(12):1227-1240.
[13] GUO B, HUANG X, ZHANG F, et al. Classification of airborne laser scanning data using JointBoost[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2015, 100:71-83.
[14] BLOMLEY R, JUTZI B, WEINMANN M. Classification of airborne laser scanning data using geometric multi-scale features and different neighbourhood types[J]. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016,Ⅲ-3(3):169-176.
[15] WEINMANN M, JUTZI B, HINZ S, et al. Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 105:286-304.

多尺度邻域特征下的机载LiDAR点云电力线分类

Power line classification from airborne LiDAR data via multi-scale neighborhood features

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价

[1]	王道杰, 陈倍, 孙健辉. 机载LiDAR点云密度对DEM精度的影响[J]. 测绘通报, 2022, 0(5): 140-144,169.
[2]	高胜超, 高彦涛, 王文杰. 机载LiDAR在河南省重点水库库区高精度DEM建立中的应用[J]. 测绘通报, 2022, 0(1): 128-132.
[3]	李德友, 李彩林, 李祥珅, 王柏涛. 激光雷达点云电力线自动提取算法[J]. 测绘通报, 2021, 0(6): 33-38.
[4]	张鹏, 马庆勋, 吕杰, 季金亮, 李紫微. 机器学习算法在森林地上生物量估算中的应用[J]. 测绘通报, 2021, 0(12): 28-32.
[5]	吉绪发. 旋翼无人机载激光雷达在农村不动产权籍调查中的应用[J]. 测绘通报, 2020, 0(7): 152-155,158.
[6]	周钦坤, 岳建平, 杨恒, 朱依民. 机载LiDAR数据中电力线的自动提取与重建[J]. 测绘通报, 2020, 0(10): 26-30,37.
[7]	胡耀锋, 胡欣然. 基于LiDAR的城市坐标系精度评估及应用[J]. 测绘通报, 2020, 0(10): 101-105.
[8]	朱依民, 田林亚, 毕继鑫, 林松. 基于机载LiDAR数据的建筑物轮廓提取[J]. 测绘通报, 2019, 0(12): 65-70.
[9]	杨明军, 苏春梅, 康冰锋, 张珣, 曹殿才. 平原地区机载激光雷达数据的抽稀算法分析[J]. 测绘通报, 2019, 0(1): 101-107.
[10]	彭劲松, 许俊, 李娟, 周光明. 机载激光测量系统在地质灾害中的应用[J]. 测绘通报, 2018, 0(9): 160-162.
[11]	胡耀锋, 张志媛, 林鸿. 利用机载LiDAR测绘大比例尺数字地形图的可行性研究[J]. 测绘通报, 2015, 0(5): 87-90.
[12]	杨庚印. 山西省高精度数字高程模型建设方案设计与实现[J]. 测绘通报, 2014, 0(9): 76-80.
[13]	熊爱武杨蒙蒙. 机载LiDAR点云数据误差分析[J]. 测绘通报, 2014, 0(3): 75-78.