YOLO-Based Real-Time Detection of Power Line Poles from Unmanned Aerial Vehicle Inspection Vision

doi:10.11930/j.issn.1004-9649.201812028

Abstract

Abstract: Unmanned aerial vehicles (UAV)-based inspection has become an important approach for power line inspection after disaster. However, the current UAV-based inspection is still performed manually for damage assessments, which is not only time-consuming but also poor in accuracy. In this paper a real-time detection model based on YOLO deep learning algorithm is presented to detect the status of power line poles automatically from the UAV vision data after disaster. The data augmentation is performed for collapsed towers to solve the class imbalance problem. To improve the parameters of YOLO, K-means algorithm is used to cluster object frames of pole data. The experimental results show that the proposed model can effectively detect multi-scale towers in multiple environments. The Recall and Intersection-over-Union (IoU) of the improved YOLO are improved, with the mean average precision (mAP) on the test set of 94.09% and the average processing speed of 20 frames per second (FPS) after improving the parameters. Moreover, we tested the simplified YOLO with faster speed, and the average processing speed reaches 30 FPS.

Key words: UAV inspection, power line poles, deep learning, YOLO, data augmentation, artificial intelligence and big data application

CLC Number:

TM755

GUO Jingdong, CHEN Bin, WANG Renshu, WANG Jiayu, ZHONG Linlin. YOLO-Based Real-Time Detection of Power Line Poles from Unmanned Aerial Vehicle Inspection Vision[J]. Electric Power, 2019, 52(7): 17-23.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.201812028

https://www.electricpower.com.cn/EN/Y2019/V52/I7/17

References

[1] 韩冰, 尚方. 面向无人机输电线路巡检的电力杆塔检测框架模型[J]. 浙江电力, 2016, 35(4):6-11 HAN Bing, SHANG Fang. Power tower detection framework model for UAV transmission line inspection[J]. Zhejiang Electric Power, 2016, 35(4):6-11
[2] KATRASNIK, PERNUS, LIKAR. A survey of mobile robots for distribution power line inspection[J]. IEEE Transactions on Power Delivery, 2009, 25(1):485-493.
[3] ROVERSO D, NGUYEN V N, JENSSEN R. Automatic autonomous vision-based power line inspection:a review of current status and the potential role of deep learning[J]. International Journal of Electrical Power & Energy Systems, 2018, 99(7):107-120.
[4] TOTH J, GILPIN-JACKSON A. Smart view for a smart grid:unmanned aerial vehicles for transmission lines[C]//International Conference on Applied Robotics for the Power Industry Montreal. Montreal, Canada:IEEE, 2010:1-6.
[5] DENG C, WANG S, HUANG Z, et al. Unmanned aerial vehicles for power line inspection:a cooperative way in platforms and communications[J]. Journal of Communications, 2014, 9(9):687-692.
[6] 章绍耕. 浅谈"抗台风"电网抢修物资供应过程中所应注意的问题[J]. 农电管理, 2017(3):28-29 ZHANG Shaogeng. A brief discussion on the problems in the material supply and emergency repair process of power grid in anti-typhoon[J]. Rural Power Management, 2017(3):28-29
[7] 王万国, 田兵, 刘越, 等. 基于RCNN的无人机巡检图像电力小部件识别研究[J]. 地球信息科学学报, 2017, 19(2):256-263 WANG Wanguo, TIAN Bing, LIU Yue, et al. Research on power component recognition of unmanned aerial vehicle inspection image based on RCNN[J]. Geo-Information Science, 2017, 19(2):256-263
[8] 杨晓旭, 温招洋. 深度学习在输电线路绝缘子故障检测中的研究与应用[J]. 中国新通信, 2018, 20(10):208-210 YANG Xiaoxu, WEN Zhaoyang. Research and application of deep learning in fault detection of transmission line insulators[J]. China New Telecommunications, 2018, 20(10):208-210
[9] NORDENG I E, HASAN A, OLSEN D, et al. DEBC detection with deep learning[C]//Scandinavian Conference on Image Analysis. Troms, Norway:Springer, 2017:248−259.
[10] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
[11] LIU W, ANGUELOV D, ERHAN D, et al. SSD:single shot multibox detector[C]//European Conference on Computer Vision. Amsterdam, Netherlands:Springer, 2016:21-37.
[12] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once:unified, real-time object detection[C]//Computer Vision and Pattern Recognition. Las Vegas, USA:IEEE, 2016:779-788.
[13] REDMON J, FARHADI A. YOLO9000:better, faster, stronger[C]//IEEE Conference on Computer Vision and Pattern Recognition. Hawaii, USA:IEEE, 2017:6517−6525.
[14] REDMON J, FARHADI A. YOLOv3:an incremental improvement[DB/OL]. (2018-04-08)[2018-10-18]. http//arXiv.org/pdf/1804.02767.pdf.
[15] HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//Conference on Computer Vision and Pattern Recognition. Hawaii, USA:IEEE, 2017:2980-2988.
[16] MARTINEZ C, SAMPEDRO, CHAUHAN A, et al. Towards autonomous detection and tracking of electric towers for aerial power line inspection[C]//International Conference on Unmanned Aircraft Aystems. Orlando, USA:IEEE, 2014:284−295.
[17] 苑津莎, 崔克彬, 李宝树. 基于ASIFT算法的绝缘子视频图像的识别与定位[J]. 电测与仪表, 2015, 52(7):106-112 YUAN Jinsha, CUI Kebin, LI Baoshu. Recognition and location of insulator video and image by ASIFT-based algorithm[J]. Electrical Measurement Instrumentation, 2015, 52(7):106-112
[18] GERKE M, SEIBOLD P. Visual inspection of power lines by UAS[C]//International Conference and Exposition on Electrical and Power Engineering. Iasi, Romania:IEEE, 2014:284−295.
[19] KRAWCZYK B. Learning from imbalanced data:open challenges and future directions[J]. Progress in Artificial Intelligence, 2016, 5(4):1-12.
[20] OUYANG W, WANG X, ZHANG C, et al. Factors in fine tuning deep model for object detection with long-tail distribution[C]//Computer Vision and Pattern Recognition. Las Vegas, USA:IEEE, 2016:864−873.
[21] ENGSTROM L, TSIPRAS D, SCHMIDT L, et al. A rotation and a translation suffice:fooling CNNs with simple transformations[DB/OL]. (2017-12-07)[2018-01-20]. http//arXiv.org/pdf/1712.02779.pdf.