{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T14:25:37Z","timestamp":1774362337371,"version":"3.50.1"},"reference-count":48,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2018,11,8]],"date-time":"2018-11-08T00:00:00Z","timestamp":1541635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010193","name":"Korea Electric Power Corporation","doi-asserted-by":"publisher","award":["\u201cStudy for Diagnosis and Life Cycle Evaluation of Polymer Insulator\u201d project supported by 2017 Main R&D Projects"],"award-info":[{"award-number":["\u201cStudy for Diagnosis and Life Cycle Evaluation of Polymer Insulator\u201d project supported by 2017 Main R&D Projects"]}],"id":[{"id":"10.13039\/501100010193","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Electric power line equipment such as insulators, cut-out-switches, and lightning-arresters play important roles in ensuring a safe and uninterrupted power supply. Unfortunately, their continuous exposure to rugged environmental conditions may cause physical or electrical defects in them which may lead to the failure to the electrical system. In this paper, we present an automatic real-time electrical equipment detection and defect analysis system. Unlike previous handcrafted feature-based approaches, the proposed system utilizes a Convolutional Neural Network (CNN)-based equipment detection framework, making it possible to detect 17 different types of powerline insulators in a highly cluttered environment. We also propose a novel rotation normalization and ellipse detection method that play vital roles in the defect analysis process. Finally, we present a novel defect analyzer that is capable of detecting gunshot defects occurring in electrical equipment. The proposed system uses two cameras; a low-resolution camera that detects insulators from long-shot images, and a high-resolution camera which captures close-shot images of the equipment at high-resolution that helps for effective defect analysis. We demonstrate the performances of the proposed real-time equipment detection with up to 93% recall with 92% precision, and defect analysis system with up to 98% accuracy, on a large evaluation dataset. Experimental results show that the proposed system achieves state-of-the-art performance in automatic powerline equipment inspection.<\/jats:p>","DOI":"10.3390\/s18113837","type":"journal-article","created":{"date-parts":[[2018,11,9]],"date-time":"2018-11-09T03:08:02Z","timestamp":1541732882000},"page":"3837","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["Robust Powerline Equipment Inspection System Based on a Convolutional Neural Network"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6996-1622","authenticated-orcid":false,"given":"Zahid Ali","family":"Siddiqui","sequence":"first","affiliation":[{"name":"Department of Computer Science &amp; Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea"},{"name":"Department of Electronic Engineering, NED University of Engineering &amp; Technology, Karachi-75270, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Unsang","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Computer Science &amp; Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8117-6566","authenticated-orcid":false,"given":"Sang-Woong","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Software, Gachon University, 1342 Seongnamdae-ro, Sujeong-gu, Seongnam 13120, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nam-Joon","family":"Jung","sequence":"additional","affiliation":[{"name":"Smart Distribution Lab. SW Platform Center, KEPCO Research Institute, 105 Moonji-ro, Daejeon 34056, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minhee","family":"Choi","sequence":"additional","affiliation":[{"name":"Smart Distribution Lab. SW Platform Center, KEPCO Research Institute, 105 Moonji-ro, Daejeon 34056, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chanuk","family":"Lim","sequence":"additional","affiliation":[{"name":"Smart Distribution Lab. SW Platform Center, KEPCO Research Institute, 105 Moonji-ro, Daejeon 34056, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jang-Hun","family":"Seo","sequence":"additional","affiliation":[{"name":"ST Vision, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2018,11,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Mei, X., Lu, T., Wu, X., and Zhang, B. (2012, January 27\u201329). Insulator surface dirt image detection technology based on improved watershed algorithm. Proceedings of the 2012 Asia-Pacific Power and Energy Engineering Conference, Shanghai, China.","DOI":"10.1109\/APPEEC.2012.6307691"},{"key":"ref_2","unstructured":"Li, J., Li, M., and Wang, Q. (2017, January 18\u201321). A novel insulator detection method for aerial images. Proceedings of the 9th International Conference on Computer and Automation Engineering, Sydney, Australia."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3613","DOI":"10.1109\/TGRS.2013.2274101","article-title":"An active contour model based on texture distribution for extracting inhomogeneous insulators from aerial images","volume":"52","author":"Wu","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1109\/TPWRD.2007.908779","article-title":"Comparison of DC pollution flashover performances of various types of porcelain, glass, and composite insulators","volume":"23","author":"Jiang","year":"2008","journal-title":"IEEE Trans. Power Deliv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2328","DOI":"10.1109\/TIM.2009.2013924","article-title":"Optical detection of partial discharges on insulator strings of high-voltage transmission lines","volume":"58","author":"Oliveira","year":"2009","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Shong, K.M., Kim, Y.S., and Kim, S.G. (2007, January 6\u20138). Images detection and diagnosis of corona discharge on porcelain insulators at 22.9kV D\/L. Proceedings of the IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives, Cracow, Poland.","DOI":"10.1109\/DEMPED.2007.4393138"},{"key":"ref_7","unstructured":"Yang, T.W., Yin, H., Ruan, Q.Q., da Han, J., Qi, J.T., Yong, Q., Wang, Z.T., and Sun, Z.Q. (2012, January 28\u201330). Overhead power line detection from UAV video images. Proceedings of the 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP), Auckland, New Zealand."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Yetgin, \u00d6.E., \u015eent\u00fcrk, Z., and Gerek, \u00d6.N. (2015, January 26\u201328). A comparison of line detection methods for power line avoidance in aircrafts. Proceedings of the 9th International Conference on Electrical and Electronics Engineering (ELECO), Bursa, Turkey.","DOI":"10.1109\/ELECO.2015.7394489"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Liu, Y., Mejias, L., and Li, Z. (September, January 25). Fast power line detection and localization using steerable filter for active UAV guidance. Proceedings of the 12th International Society for Photogrammetry and Remote Sensing (ISPRS2012), Melbourne, Australia.","DOI":"10.5194\/isprsarchives-XXXIX-B3-491-2012"},{"key":"ref_10","first-page":"827","article-title":"Towards visual based navigation with power line detection","volume":"Volume 8887","author":"Bebis","year":"2014","journal-title":"Advances in Visual Computing, ISVC 2014, Lecture Notes in Computer Science"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Sampedro, C., Martinez, C., Chauhan, A., and Campoy, P. (2014, January 6\u201311). A supervised approach to electric tower detection and classification for power line inspection. Proceedings of the 2014 International Joint Conference on Neural Networks (IJCNN), Beijing, China.","DOI":"10.1109\/IJCNN.2014.6889836"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Han, B., and Wang, X. (2016). Learning for tower detection of power line inspection. DEStech Trans. Comput. Sci. Eng., 216\u2013220.","DOI":"10.12783\/dtcse\/iccae2016\/7194"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Martinez, C., Sampedro, C., Chauhan, A., and Campoy, P. (2014, January 27\u201330). Towards autonomous detection and tracking of electric towers for aerial power line inspection. Proceedings of the International Conference on Unmanned Aircraft Systems (ICUAS), Orlando, FL, USA.","DOI":"10.1109\/ICUAS.2014.6842267"},{"key":"ref_14","first-page":"127","article-title":"Defects detection of glass insulator based on color image","volume":"35","author":"Lin","year":"2011","journal-title":"Power Syst. Technol."},{"key":"ref_15","first-page":"194","article-title":"A method to extract insulator image from aerial image of helicopter patrol","volume":"34","author":"Huang","year":"2010","journal-title":"Power Syst. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Li, W.G., Ye, G., Huang, F., Wang, S., and Chang, W.Z. (2010, January 16\u201318). Recognition of insulator based on developed MPEG-7 texture feature. Proceedings of the 3rd International Congress on Image and Signal Processing, Yantai, China.","DOI":"10.1109\/CISP.2010.5648283"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhang, X., An, J., and Chen, F. (2010, January 11\u201312). A simple method of tempered glass insulator recognition from airborne image. Proceedings of the 2010 International Conference on Optoelectronics and Image Processing, Haikou, China.","DOI":"10.1109\/ICOIP.2010.23"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1109\/TDEI.2016.005896","article-title":"Digital image processing techniques for estimating power released from the corona discharges","volume":"24","author":"Prasad","year":"2017","journal-title":"IEEE Trans. Dielectr. Electr. Insul."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2012\/935073","article-title":"Adaptive forming of the beam pattern of microstrip antenna with the use of an artificial neural network","volume":"2012","author":"Dudczyk","year":"2012","journal-title":"Int. J. Antennas Propag."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Matuszewski, J., and Sikorska-\u0141ukasiewicz, K. (2017, January 28\u201330). Neural network application for emitter identification. Proceedings of the 2017 18th International Radar Symposium (IRS), Prague, Czech Republic.","DOI":"10.23919\/IRS.2017.8008202"},{"key":"ref_21","unstructured":"Zhang, J., and Yang, R. (2006, January 20\u201324). Insulators recognition for 220kv\/330kv high-voltage live-line cleaning robot. Proceedings of the 18th International Conference on Pattern Recognition (ICPR\u201906), Hong Kong, China."},{"key":"ref_22","unstructured":"Huang, D.S., Jiang, C., Bevilacqua, V., and Figueroa, J.C. (2012). Detecting insulators in the image of overhead transmission lines. Intelligent Computing Technology. ICIC 2012. Lecture Notes in Computer Science, Springer."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"963","DOI":"10.1109\/LGRS.2014.2369525","article-title":"A robust insulator detection algorithm based on local features and spatial orders for aerial images","volume":"12","author":"Liao","year":"2015","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_24","first-page":"7","article-title":"A method of insulator detection from aerial images","volume":"177","author":"Zhai","year":"2014","journal-title":"Sens. Transducers"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, D., Cong, Y., Xia, Y., and Tang, Y. (2012, January 14\u201316). A method of insulator detection from video sequence. Proceedings of the 2012 Fourth International Symposium on Information Science and Engineering, Shanghai, China.","DOI":"10.1109\/ISISE.2012.93"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Wang, X., and Zhang, Y. (2016, January 7\u201310). Insulator identification from aerial images using support vector machine with background suppression. Proceedings of the 2016 International Conference on Unmanned Aircraft Systems (ICUAS), Arlington, VA, USA.","DOI":"10.1109\/ICUAS.2016.7502544"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1109\/TDEI.2010.5412006","article-title":"Insulator condition analysis for overhead distribution lines using combined wavelet and support vector machine (SVM)","volume":"17","author":"Murthy","year":"2010","journal-title":"IEEE Trans. Dielectr. Electr. Insul."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1049\/iet-ipr.2009.0293","article-title":"Digital image processing approach using combined wavelet hidden Markov model for well-being analysis of insulators","volume":"5","author":"Murthy","year":"2011","journal-title":"IET Image Process."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Jabid, T., and Uddin, M.Z. (2016, January 28\u201329). Rotation invariant power line insulator detection using local directional pattern and support vector machine. Proceedings of the 2016 International Conference on Innovations in Science, Engineering and Technology (ICISET), Dhaka, Bangladesh.","DOI":"10.1109\/ICISET.2016.7856522"},{"key":"ref_30","unstructured":"Oberweger, M., Wendel, A., and Bischof, H. (2014, January 1). Visual recognition and fault detection for power line insulators. Proceedings of the 19th Computer Vision Winter Workshop, Krtiny, Czech Republic."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Razavian, A.S., Azizpour, H., Sullivan, J., and Carlsson, S. (2014, January 23). CNN features off-the-shelf: An astounding baseline for recognition. Proceedings of the Computer Vision and Pattern Recognition Workshops, Columbus, OI, USA.","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Xu, G., Qi, Y., Liu, N., and Zhang, T. (2016, January 24\u201329). Multi-patch deep features for power line insulator status classification from aerial images. Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, Canada.","DOI":"10.1109\/IJCNN.2016.7727606"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"35316","DOI":"10.1109\/ACCESS.2018.2846293","article-title":"Insulator fault detection based on spatial morphological features of aerial images","volume":"6","author":"Zhai","year":"2018","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhai, Y., Cheng, H., Chen, R., Yang, Q., and Li, X. (2018). Multi-saliency aggregation-based approach for insulator flashover fault detection using aerial images. Energies, 11.","DOI":"10.3390\/en11020340"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1117\/1.JEI.26.6.063014","article-title":"Automatic identification and location technology of glass insulator self-shattering","volume":"26","author":"Huang","year":"2017","journal-title":"J. Electron. Imaging"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"3421","DOI":"10.1109\/TDEI.2015.004741","article-title":"Localization of multiple insulators by orientation angle detection and binary shape prior knowledge","volume":"22","author":"Zhao","year":"2015","journal-title":"IEEE Trans. Dielectr. Electr. Insul."},{"key":"ref_37","first-page":"1","article-title":"Computer vision\u2013based automatic rod-insulator defect detection in high-speed railway catenary system","volume":"2018","author":"Han","year":"2018","journal-title":"Intern. J. Adv. Robot. Syst."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Iruansi, U., Tapamo, J.R., and Davidson, I.E. (2015, January 14\u201317). An active contour approach to insulator segmentation. Proceedings of the AFRICON 2015, Addis Ababa, Ethiopia.","DOI":"10.1109\/AFRCON.2015.7331976"},{"key":"ref_39","unstructured":"Redmon, J. (2018, October 02). Darknet: Open Source Neural Networks in C. Available online: http:\/\/pjreddie.com\/darknet\/."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Redmon, J., and Farhadi, A. (2017, January 21\u201326). YOLO9000: Better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"3693","DOI":"10.1016\/j.patcog.2014.05.012","article-title":"A fast and effective ellipse detector for embedded vision applications","volume":"47","author":"Fornaciari","year":"2014","journal-title":"Patten Recognit."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"804","DOI":"10.1007\/s12555-014-0561-y","article-title":"Fast ellipse detection based on three point algorithm with edge angle information","volume":"14","author":"Kwon","year":"2016","journal-title":"Int. J. Control Autom. Syst."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1109\/34.765658","article-title":"Direct least square fitting of ellipses","volume":"21","author":"Fitzgibbon","year":"1999","journal-title":"IEEE Trans. Patten Anal. Mach. Intell."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1651","DOI":"10.1109\/61.634186","article-title":"Gunshot damage to ceramic and non-ceramic insulators","volume":"2","author":"Burnham","year":"1997","journal-title":"IEEE Trans. Power Deliv."},{"key":"ref_45","unstructured":"Electric Power Research Institute (2018, November 08). Field Guide: Visual Inspection of Polymer Insulators. Available online: https:\/\/www.epri.com\/#\/pages\/product\/3002003720\/."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.patcog.2009.06.014","article-title":"Measure of circularity for parts of digital boundaries and its fast computation","volume":"43","author":"Roussillon","year":"2010","journal-title":"Patten Recognit."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (VOC) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Intern. J. Comput. Vis."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Pietrow, D., and Matuszewski, J. (2017, January 12\u201314). Objects detection and recognition system using artificial neural networks and drones. Proceedings of the Signal Processing Symposium (SPSympo), Jachranka, Poland.","DOI":"10.1109\/SPS.2017.8053689"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/11\/3837\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:28:44Z","timestamp":1760196524000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/11\/3837"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,8]]},"references-count":48,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2018,11]]}},"alternative-id":["s18113837"],"URL":"https:\/\/doi.org\/10.3390\/s18113837","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,8]]}}}