复杂场景下的电力线自动提取

doi:10.13474/j.cnki.11-2246.2021.0231

测绘通报 ›› 2021, Vol. 0 ›› Issue (8): 1-6.doi: 10.13474/j.cnki.11-2246.2021.0231

• 学术研究 • 下一篇

复杂场景下的电力线自动提取

赵延峰, 胡耀垓, 王先培, 赵乐

武汉大学电子信息学院, 湖北武汉 430070

收稿日期:2020-10-14 修回日期:2021-06-22 发布日期:2021-08-30
作者简介:赵延峰(1995-),男,硕士生,主要研究方向为电力线提取。E-mail:yanfengzhao@whu.edu.cn
基金资助:
国家自然科学基金（51707135）

Automatic power line extraction algorithm in complex scene

ZHAO Yanfeng, HU Yaogai, WANG Xianpei, ZHAO Le

School of Electronic Information, Wuhan University, Wuhan 430070, China

Received:2020-10-14 Revised:2021-06-22 Published:2021-08-30

摘要/Abstract

摘要： 实现复杂场景下航拍图像的端到端电力线提取是电力线无人机检测的关键。本文通过分析基于深度学习的电力线实例分割实现存在的问题，提出了一种基于改进Mask R-CNN的电力线自动提取算法。首先，根据电力线的线性特征，提出一种线性IoU计算方法，改进Mask R-CNN原有的IoU计算，提高电力线提取性能；然后，将改进后的网络在电力线数据集上进行训练，得到电力线粗提取结果；最后，通过线段编组拟合算法，对粗提取结果进行聚类拟合，以解决电力线断裂和误检的问题。试验结果表明，所提方法能从环境复杂的无人机航拍图像中较为准确地提取完整的电力线。

关键词: 电力线提取, 无人机, Mask R-CNN, 线性IoU, 线段编组拟合

Abstract: End-to-end power line extraction from aerial images in complex scenes is the key to power line detection by UAVs. In this paper, an automatic power line extraction algorithm based on improved Mask R-CNN is proposed by analyzing the problems existing in the realization of power line instance segmentation based on deep learning. First of all, according to the linear characteristic of power line, this paper puts forward a kind of improved Mask R linear IoU calculation method, a CNN original IoU calculation, improve the performance of power line extraction. Then the improved network on the power line data set for training, power line crude extraction results. Finally through a line marshalling fitting method, the result of the crude extract clustering fitting, to solve the problem of power line breakage and misdetection. Experimental results show that the proposed method can accurately extract the complete power lines from UAV aerial images with complex environment.

Key words: power line extraction, UAV, Mask R-CNN, linear IoU, line segment group fitting

中图分类号:

赵延峰, 胡耀垓, 王先培, 赵乐. 复杂场景下的电力线自动提取[J]. 测绘通报, 2021, 0(8): 1-6.

ZHAO Yanfeng, HU Yaogai, WANG Xianpei, ZHAO Le. Automatic power line extraction algorithm in complex scene[J]. Bulletin of Surveying and Mapping, 2021, 0(8): 1-6.

参考文献

[1] BERNI J, ZARCO-TEJADA P J, SUAREZ L, et al. Thermal and narrowband multispectral remote sensing for vegetation monitoring from an unmanned aerial vehicle[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(3):722-738.
[2] POULIOT N, RICHARD P L, MONTAMBAULT S. LineScout technology opens the way to robotic inspection and maintenance of high-voltage power lines[J]. IEEE Power and Energy Technology Systems Journal, 2015, 2(1):1-11.
[3] ARAAR O, AOUF N, DIETZ J L V. Power pylon detection and monocular depth estimation from inspection UAVs[J]. Industrial Robot, 2015, 42(3):200-213.
[4] 彭向阳, 陈驰, 饶章权, 等. 基于无人机多传感器数据采集的电力线路安全巡检及智能诊断[J]. 高电压技术, 2015, 41(1):159-166.
[5] 赵乐, 王先培, 代荡荡, 等. 复杂背景下电力线自动提取算法[J]. 高电压技术, 2019, 45(1):218-227.
[6] 陈建, 沈潇军, 姚一杨, 等. 基于航拍图像的输电线检测方法[J]. 计算机工程与设计, 2018, 39(4):1155-1160.
[7] 张从新, 赵乐, 王先培. 复杂地物背景下电力线的快速提取算法[J]. 武汉大学学报(工学版), 2018, 51(8):732-739.
[8] 赵浩程, 雷俊峰, 王先培, 等. 背景复杂下航拍图像的电力线识别算法[J]. 测绘通报, 2019(7):28-32.
[9] 高旭东. 无人机线路巡检安全距离的分析与测量[D]. 太原:太原理工大学, 2019.
[10] TIAN F, WANG Y, ZHU L. Power line recognition and tracking method for UAVs inspection[C]//Proceedings of the 2015 IEEE International Conference on Information and Automation, Lijiang:IEEE, 2015:2136-2141.
[11] KATRASNIK J, PERNUS F, LIKAR B. A survey of mobile robots for distribution power line inspection[J]. IEEE Transactions on Power Delivery, 2010, 25(1):485-493.
[12] SONG B, LI X. Power line detection from optical images[J]. Neurocomputing, 2014, 129:350-361.
[13] LIU X, HOU L, JU X. A method for detecting power lines in UAV aerial images[C]//Proceedings of the 3rd IEEE International Conference on Computer and Communications (ICCC). Chengdu:IEEE, 2017:2132-2136.
[14] PAN C, CAO X, WU D. Power line detection via back-ground noise removal[C]//Proceedings of 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP). Washington:IEEE, 2016:871-875.
[15] YETGIN Ö E, BENLIGIRAY B, GEREK Ö N. Power line recognition from aerial images with deep learning[J]. IEEE Transactions on Aerospace and Electronic Systems, 2019, 55(5):2241-2252.
[16] 赵乐, 王先培, 姚鸿泰, 等. 基于可见光航拍图像的电力线提取算法综述[J]. 电网技术, 2021, 45(4):1536-1546.
[17] HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2):386-397.
[18] HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[C]//Proceeding of 2016 IEEE Conference on Computer Vsion and Pattern Recongnition(CVPR). LasVegas:IEEE, 2016:770-778.
[19] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature Pyramid Networks for Object Detection[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu:IEEE, 2017:936-944.
[20] MA J, SHAO W, YE H, et al. Arbitrary-oriented scene text detection via rotation proposals[J]. IEEE Transactions on Multimedia, 2018, 20(11):3111-3122.

复杂场景下的电力线自动提取

Automatic power line extraction algorithm in complex scene

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	胡义强, 杨骥, 荆文龙, 彭小燕, 蓝文陆, 彭梦微, 张雨萌. 茅尾海入海河口池塘养殖污染状况遥感调查[J]. 测绘通报, 2022, 0(7): 12-17,53.
[2]	冉崇宪, 李森磊. 利用无人机多光谱影像提取树冠信息[J]. 测绘通报, 2022, 0(7): 112-117.
[3]	刘玉贤, 阮明浩, 闫臻. 一种基于机载激光点云的门型电塔精确提取方法[J]. 测绘通报, 2022, 0(7): 129-133.
[4]	周烨, 刘云波, 郑丽波, 龙泱君. 多平台点云数据的单木参数提取精度分析[J]. 测绘通报, 2022, 0(7): 168-172.
[5]	胡义强, 杨骥, 荆文龙, 杨传训, 舒思京, 李勇. 基于无人机遥感的海岸带生态环境监测研究综述[J]. 测绘通报, 2022, 0(6): 18-24.
[6]	周建国, 罗超, 彭朵. 微型无人机辅助的三角高程测量方法[J]. 测绘通报, 2022, 0(6): 71-75.
[7]	刘耀辉, 于祥惠, 范洁洁, 周洁, 程昊, 姚国标, 孟飞, 靳奉祥. 基于无人机影像和面向对象的中国西部地区农村宅基地面积快速估算[J]. 测绘通报, 2022, 0(6): 125-129.
[8]	万忠明, 王亚文, 范子义. 无人机倾斜摄影技术在边坡监测中的应用[J]. 测绘通报, 2022, 0(6): 170-172.
[9]	王广帅. 无人机倾斜摄影铁路轨道线高精度自动重建[J]. 测绘通报, 2022, 0(5): 133-139,156.
[10]	毕瑞, 甘淑, 袁希平, 李绕波, 高莎. 不同地形环境下无人机航线规划及三维建模分析[J]. 测绘通报, 2022, 0(4): 83-89,129.
[11]	任旭斌, 康建锋, 于东海. 无人机倾斜摄影测量在房屋建筑面积测算中的应用[J]. 测绘通报, 2022, 0(3): 116-120,126.
[12]	蔡嘉伦, 贾洪果, 刘国祥, 张波, 刘巧, 吴仁哲, 向卫, 毛文飞, 张瑞. 对比传统低空航测的无人机倾斜摄影测量精度评估[J]. 测绘通报, 2022, 0(2): 31-36.
[13]	贾煜, 汪泓, 蔡宏, 张磊. 结合地形因子与分层策略的喀斯特地区无人机影像分类[J]. 测绘通报, 2022, 0(2): 121-127.
[14]	范媛, 范宏, 吴建国, 林峻, 陈吉军, 巴日斯, 郑江华. 无人机影像识别白喉乌头的相对高程阈值法适用性分析[J]. 测绘通报, 2022, 0(2): 131-135.
[15]	高莎, 袁希平, 甘淑, 杨明龙, 袁新悦, 罗为东. 融合无人机影像与LiDAR点云的山区地表覆被景观特征探测[J]. 测绘通报, 2022, 0(1): 110-115.