摘要
针对输电线路电塔点云的归一化数字表面模型(nDSM)、局部密度和特有空间分布特征,提出一种基于二维格网特征提取和空间特征分析的电塔自动定位简化方法.首先对无人机获取的点云进行滤波去噪处理;然后对点云构建K-D树和二维格网,根据密度、nDSM统计兴趣区;最后根据其空间分布特征得到电塔的坐标.经试验验证,简化算法有效提高了自动化处理效率,算法精度达米级,基本满足电力巡检精度要求.
Based on the normalized digital surface model(nDSM),partial density and spatial distribution characteristics of transmission towers,a simplified method of positioning the tower by extracting features of a 2D grid and analyzing the spatial characteristics is proposed in the paper.First,the noises of the point cloud obtained by a UAV are filtered and canceled,then a K-D tree diagram and a 2D grid are built based on the density and nDSM statistics region of interest,and at last the coordinate of the tower from its spatial characteristics is calculated.The experiment turns out that this simplified method effectively improves the automatic process with an accuracy of meter-level which basically meets the requirements of power patrol inspection on accuracy.
作者
危双丰
尹思铭
习晓环
王濮
WEI Shuangfeng;YIN Siming;XI Xiaohuan;WANG Pu(School of Geomatics and Urban Information, Beijing University of Civil Engineering and Architecture, Beijing 100044;Beijing Advanced Innovation Center for Future Urban Design, Beijing University of Civil Engineering and Architecture, Beijing 100044;Engineering Research Center of Representative Building and Architectural Heritage Database, Ministry of Education, Beijing University of Civil Engineering and Architecture, Beijing 100044;Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094)
出处
《北京建筑大学学报》
2020年第3期44-50,共7页
Journal of Beijing University of Civil Engineering and Architecture
基金
国家自然科学基金项目(41601409)
北京市自然科学基金项目(8172016)。
关键词
输电线路
激光点云
点云分类
电塔定位
transmission line
laser point cloud
drone inspection
automatic positioning of the tower
