首页 > 论文 > 激光与光电子学进展 > 57卷 > 20期(pp:201502--1)

基于关键点的输电线路防振锤滑移视觉检测

Visual Detection of Stockbridge Damper Slip on Power Transmission Lines Based on Key Points

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

提出一种基于关键点训练学习的防振锤滑移检测方法。首先利用改进SSD模型对防振锤进行识别、定位;再选择防振锤关键点,训练MobileNetV3网络,通过上一级定位结果设定输入区域,从而实现关键点的检测;最后依据线路图像特征,制定相应判别规则。当档距内悬挂m(m≥2)个防振锤时,利用关键点几何约束关系实现判别;当档距内悬挂单防振锤时,采用EPnP算法估计相机在多个角度的位姿,通过位姿与线夹关键点像素坐标间的关系求解最邻近点的世界坐标,判断最邻近点与防振锤间的距离是否在阈值范围内。实验结果表明,所提方法能对滑移异常进行有效识别,为输电线路异常检测提供了新思路。

Abstract

This study proposes a method for detecting slipping of stockbridge dampers based on key point training and learning. First, an improved SSD model is used to identify and locate the stockbridge damper. Thereafter, the key points of the stockbridge damper are selected, the MobileNetV3 network is trained, and the input area is set by the upper positioning results of the stockbridge damper to realize the detection of key points. Finally, discrimination rules are formulated according to the characteristics of line images. For m(m≥2) stockbridge dampers, the geometric constraint relationship among the key points is used to realize determination. For a single stockbridge damper, the EPnP algorithm is used to estimate the multiangle pose of the camera. Moreover, the spatial coordinates of the nearest points are obtained from the relationship between the pose and the pixel coordinates of the key point of the damp to determine whether the distance between the nearest points and the stockbridge damper is within the threshold range. The experimental results show that the proposed method can effectively identify slip faults and provide new ideas for detecting defects in transmission lines.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391.4

DOI:10.3788/LOP57.201502

所属栏目:机器视觉

收稿日期:2020-01-19

修改稿日期:2020-02-24

网络出版日期:2020-10-01

作者单位    点击查看

刘又维:长沙理工大学电气与信息工程学院, 湖南 长沙 410114
樊绍胜:长沙理工大学电气与信息工程学院, 湖南 长沙 410114
唐立军:云南电网有限责任公司电力科学研究院, 云南 昆明 650217
冯勇:云南电网有限责任公司电力科学研究院, 云南 昆明 650217
李浩涛:云南电网有限责任公司电力科学研究院, 云南 昆明 650217

联系人作者:刘又维(erwill@qq.com)

【1】Wang F, Wang Y, Zhou R, et al. Experiments on aeolian vibration of large span overhead transmission lines [J]. Journal of Chongqing University. 2018, 41(1): 42-50.
汪峰, 王宇, 周蕊, 等. 架空输电线路大跨越导线微风振动试验 [J]. 重庆大学学报. 2018, 41(1): 42-50.
Wang F, Wang Y, Zhou R, et al. Experiments on aeolian vibration of large span overhead transmission lines [J]. Journal of Chongqing University. 2018, 41(1): 42-50.
汪峰, 王宇, 周蕊, 等. 架空输电线路大跨越导线微风振动试验 [J]. 重庆大学学报. 2018, 41(1): 42-50.

【2】Xia H X, Xia D S. Analysis of damper clamp slippage and preventive measures [J]. Electric Power Construction. 2008, 29(8): 108-109.
夏泓轩, 夏德森. 防振锤线夹滑移分析及预防措施 [J]. 电力建设. 2008, 29(8): 108-109.

【3】Ma L T, Zheng S H, Zhu Y K, et al. Fracture analysis of overhead transmission line dampers in the eastern region of Inner Mongolia [J]. Northeast Electric Power Technology. 2018, 39(4): 4-7,10.
马龙涛, 郑树会, 祝永坤, 等. 蒙东地区架空输电线路防振锤断裂破坏原因分析 [J]. 东北电力技术. 2018, 39(4): 4-7,10.

【4】Chen X J, Wu Y S, Zhao L. Identification of OPGW vibration damper based on random Hough transformation [J]. Heilongjiang Electric Power. 2010, 32(1): 1-2,5.
陈晓娟, 吴英石, 赵亮. 基于随机Hough变换的OPGW防震锤识别 [J]. 黑龙江电力. 2010, 32(1): 1-2,5.

【5】Tan L, Wang Y N, Shen C S. Vision based obstacle detection and recognition algorithm for transmission line deicing robot [J]. Chinese Journal of Scientific Instrument. 2011, 32(11): 2564-2571.
谭磊, 王耀南, 沈春生. 输电线路除冰机器人障碍视觉检测识别算法 [J]. 仪器仪表学报. 2011, 32(11): 2564-2571.

【6】Jin L J, Yan S J, Liu Y. Vibration damper recognition based on Haar-like features and cascade AdaBoost classifier [J]. Journal of System Simulation. 2012, 24(9): 1806-1809.
金立军, 闫书佳, 刘源. 基于类Haar特征与级联AdaBoost算法的防震锤识别 [J]. 系统仿真学报. 2012, 24(9): 1806-1809.

【7】Tang H W, Sun W, Zhang W Y, et al. Wavelet neural network method based on particle swarm optimization for obstacle recognition of power line deicing robot [J]. Journal of Mechanical Engineering. 2017, 53(13): 55-63.
唐宏伟, 孙炜, 张文洋, 等. 电力线除冰机器人基于粒子群优化的小波神经网络障碍物识别方法 [J]. 机械工程学报. 2017, 53(13): 55-63.

【8】Chen L L, Zhang Z D, Peng L. Real-time detection based on improved single shot MultiBox detector [J]. Laser & Optoelectronics Progress. 2019, 56(1): 011002.
陈立里, 张正道, 彭力. 基于改进SSD的实时检测方法 [J]. 激光与光电子学进展. 2019, 56(1): 011002.

【9】Liu X P, Li Y Q, Liu L, et al. Improved YOLOV3 target recognition algorithm with embedded SENet structure [J]. Computer Engineering. 2019, 45(11): 243-248.
刘学平, 李玙乾, 刘励, 等. 嵌入SENet结构的改进YOLOV3目标识别算法 [J]. 计算机工程. 2019, 45(11): 243-248.

【10】Howard A G, Zhu M L, Chen B, et al. -04-17)[2020-01-18] . 2017, org/abs/1704: 04861.Howard A G, Zhu M L, Chen B, et al. -04-17)[2020-01-18] . 2017, org/abs/1704: 04861.

【11】Huang J, Rathod V, Sun C, et al. -04-25)[2020-01-18] . 2017, org/abs/1611: 10012.Huang J, Rathod V, Sun C, et al. -04-25)[2020-01-18] . 2017, org/abs/1611: 10012.

【12】Sandler M, Howard A, Zhu M L, linear bottlenecks[EB/OL], et al. -03-21)[2020-01-18] . 2019, org/abs/1801: 04381.Sandler M, Howard A, Zhu M L, linear bottlenecks[EB/OL], et al. -03-21)[2020-01-18] . 2019, org/abs/1801: 04381.

【13】Howard A, Sandler M, Chu G, et al. -11-20)[2020-01-18] . 2019, org/abs/1905: 02244.Howard A, Sandler M, Chu G, et al. -11-20)[2020-01-18] . 2019, org/abs/1905: 02244.

【14】Zhu K, Tao P, Fu Z L, et al. Ultrasound image fixed point measurement based on landmark detection method [J]. Journal of Harbin Institute of Technology. 2018, 50(11): 67-73.
朱锴, 陶攀, 付忠良, 等. 利用关键点检测算法的超声图像定点测量 [J]. 哈尔滨工业大学学报. 2018, 50(11): 67-73.

【15】Chen P, Wang C X. IEPnP: an iterative camera pose estimation algorithm based on EPnP [J]. Acta Optica Sinica. 2018, 38(4): 0411001.
陈鹏, 王晨骁. IEPnP: 一种基于EPnP的相机位姿迭代估计算法 [J]. 光学学报. 2018, 38(4): 0411001.

【16】Li G Z. Graphical method for calculating the installation distance of earthquake vibration hammer [J]. High Voltage Technology. 1980, 53-60.
李桂中. 导地线防振锤安装距离计算的图解法 高电压技术[J]. 0, 1980(2): 53-60.

引用该论文

Liu Youwei,Fan Shaosheng,Tang Lijun,Feng Yong,Li Haotao. Visual Detection of Stockbridge Damper Slip on Power Transmission Lines Based on Key Points[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201502

刘又维,樊绍胜,唐立军,冯勇,李浩涛. 基于关键点的输电线路防振锤滑移视觉检测[J]. 激光与光电子学进展, 2020, 57(20): 201502

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF