无人机激光扫描作业杆塔位置提取算法

发布时间：2018-05-16 11:43

本文选题：输电线路 + 无人机巡检　；参考：《电网技术》2017年11期

【摘要】：基于激光点云的输电线路杆塔自动定位是电网无人机、直升机智能巡检技术应用的基础,但目前从激光点云中定位杆塔主要依赖于人工处理,工作效率低。针对如何从激光点云中自动定位杆塔这一问题,根据输电杆塔在激光点云中具有高密度、大坡度、大高差特征,提出了一种基于二维格网多维特征分析的输电杆塔自动定位方法。首先对无人机获取的激光点云进行滤波去噪处理,再对激光点云进行规则化,在此基础上计算点云的特征图像;然后结合架空线路走廊区域分析,根据密度、高差和坡度特征迭代定位出输电杆塔,最终实现了从无人机激光点云中自动定位输电杆塔位置。采用广东电网公司大型无人直升机实际巡检获取的输电线路激光点云数据对自动定位算法进行了验证,实验结果表明提出的算法具有较高的自动化程度和处理效率,对提高无人机、直升机机巡作业智能化水平具有促进作用。
[Abstract]:The automatic location of transmission line tower based on laser point cloud is the basis of the application of power system UAV and helicopter intelligent inspection technology, but at present, the location of pole tower from laser point cloud mainly depends on manual processing, and the working efficiency is low. In order to solve the problem of how to automatically locate the tower from the laser point cloud, according to the characteristics of high density, large slope and great height difference in the laser point cloud, the transmission tower has the characteristics of high density, large slope and great height difference. This paper presents an automatic location method for transmission tower based on multidimensional feature analysis of two dimensional grid. Firstly, the laser point cloud acquired by UAV is filtered and de-noised, then the laser point cloud is regularized, and the characteristic image of point cloud is calculated on this basis, and then combined with the analysis of overhead line corridor area, according to the density, The height difference and slope characteristic are used to locate the transmission tower iteratively, and the position of the transmission tower can be automatically located from the laser point cloud of UAV. The automatic location algorithm is verified by using the laser point cloud data of transmission line obtained from the actual inspection of large unmanned helicopter in Guangdong Power Grid Company. The experimental results show that the proposed algorithm has a high degree of automation and processing efficiency. It can improve the intelligence level of UAV and helicopter patrol operation.
【作者单位】：广东电网公司电力科学研究院;测绘遥感信息工程国家重点实验室(武汉大学);
【基金】：国家自然科学基金重点项目(41531177) 中国博士后科学基金(2016M600614)~~
【分类号】：TM75

【相似文献】