{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T16:04:26Z","timestamp":1776182666891,"version":"3.50.1"},"reference-count":31,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Anhui Provincial Natural Science Foundation","award":["2108085J19"],"award-info":[{"award-number":["2108085J19"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["41871302"],"award-info":[{"award-number":["41871302"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["21-22RC15"],"award-info":[{"award-number":["21-22RC15"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["2022AH010095"],"award-info":[{"award-number":["2022AH010095"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["2108085MF223"],"award-info":[{"award-number":["2108085MF223"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["2308085MF213"],"award-info":[{"award-number":["2308085MF213"]}]},{"name":"National Nature Science Foundation of China","award":["2108085J19"],"award-info":[{"award-number":["2108085J19"]}]},{"name":"National Nature Science Foundation of China","award":["41871302"],"award-info":[{"award-number":["41871302"]}]},{"name":"National Nature Science Foundation of China","award":["21-22RC15"],"award-info":[{"award-number":["21-22RC15"]}]},{"name":"National Nature Science Foundation of China","award":["2022AH010095"],"award-info":[{"award-number":["2022AH010095"]}]},{"name":"National Nature Science Foundation of China","award":["2108085MF223"],"award-info":[{"award-number":["2108085MF223"]}]},{"name":"National Nature Science Foundation of China","award":["2308085MF213"],"award-info":[{"award-number":["2308085MF213"]}]},{"name":"Scientific Research and Talent Development Foundation of the Hefei University","award":["2108085J19"],"award-info":[{"award-number":["2108085J19"]}]},{"name":"Scientific Research and Talent Development Foundation of the Hefei University","award":["41871302"],"award-info":[{"award-number":["41871302"]}]},{"name":"Scientific Research and Talent Development Foundation of the Hefei University","award":["21-22RC15"],"award-info":[{"award-number":["21-22RC15"]}]},{"name":"Scientific Research and Talent Development Foundation of the Hefei University","award":["2022AH010095"],"award-info":[{"award-number":["2022AH010095"]}]},{"name":"Scientific Research and Talent Development Foundation of the Hefei University","award":["2108085MF223"],"award-info":[{"award-number":["2108085MF223"]}]},{"name":"Scientific Research and Talent Development Foundation of the Hefei University","award":["2308085MF213"],"award-info":[{"award-number":["2308085MF213"]}]},{"name":"Program for Scientific Research Innovation Team in Colleges and Universities of Anhui Province","award":["2108085J19"],"award-info":[{"award-number":["2108085J19"]}]},{"name":"Program for Scientific Research Innovation Team in Colleges and Universities of Anhui Province","award":["41871302"],"award-info":[{"award-number":["41871302"]}]},{"name":"Program for Scientific Research Innovation Team in Colleges and Universities of Anhui Province","award":["21-22RC15"],"award-info":[{"award-number":["21-22RC15"]}]},{"name":"Program for Scientific Research Innovation Team in Colleges and Universities of Anhui Province","award":["2022AH010095"],"award-info":[{"award-number":["2022AH010095"]}]},{"name":"Program for Scientific Research Innovation Team in Colleges and Universities of Anhui Province","award":["2108085MF223"],"award-info":[{"award-number":["2108085MF223"]}]},{"name":"Program for Scientific Research Innovation Team in Colleges and Universities of Anhui Province","award":["2308085MF213"],"award-info":[{"award-number":["2308085MF213"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["2108085J19"],"award-info":[{"award-number":["2108085J19"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["41871302"],"award-info":[{"award-number":["41871302"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["21-22RC15"],"award-info":[{"award-number":["21-22RC15"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["2022AH010095"],"award-info":[{"award-number":["2022AH010095"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["2108085MF223"],"award-info":[{"award-number":["2108085MF223"]}]},{"name":"Anhui Provincial Natural Science Foundation","award":["2308085MF213"],"award-info":[{"award-number":["2308085MF213"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The accurate and efficient detection of defective insulators is an essential prerequisite for ensuring the safety of the power grid in the new generation of intelligent electrical system inspections. Currently, traditional object detection algorithms for detecting defective insulators in images face issues such as excessive parameter size, low accuracy, and slow detection speed. To address the aforementioned issues, this article proposes an insulator defect detection model based on the lightweight Faster R-CNN (Faster Region-based Convolutional Network) model (Faster R-CNN-tiny). First, the Faster R-CNN model\u2019s backbone network is turned into a lightweight version of it by substituting EfficientNet for ResNet (Residual Network), greatly decreasing the model parameters while increasing its detection accuracy. The second step is to employ a feature pyramid to build feature maps with various resolutions for feature fusion, which enables the detection of objects at various scales. In addition, replacing ordinary convolutions in the network model with more efficient depth-wise separable convolutions increases detection speed while slightly reducing network detection accuracy. Transfer learning is introduced, and a training method involving freezing and unfreezing the model is employed to enhance the network\u2019s ability to detect small target defects. The proposed model is validated using the insulator self-exploding defect dataset. The experimental results show that Faster R-CNN-tiny significantly outperforms the Faster R-CNN (ResNet) model in terms of mean average precision (mAP), frames per second (FPS), and number of parameters.<\/jats:p>","DOI":"10.3390\/s24010290","type":"journal-article","created":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T11:31:50Z","timestamp":1704281510000},"page":"290","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Lightweight Detection Methods for Insulator Self-Explosion Defects"],"prefix":"10.3390","volume":"24","author":[{"given":"Yanping","family":"Chen","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Big Data, Hefei University, Hefei 230601, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5944-4577","authenticated-orcid":false,"given":"Chong","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Big Data, Hefei University, Hefei 230601, China"}]},{"given":"Qiang","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Big Data, Hefei University, Hefei 230601, China"}]},{"given":"Zhize","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Big Data, Hefei University, Hefei 230601, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5718-0813","authenticated-orcid":false,"given":"Le","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Big Data, Hefei University, Hefei 230601, China"}]},{"given":"Guanhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Big Data, Hefei University, Hefei 230601, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0464-6955","authenticated-orcid":false,"given":"Wenbo","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230001, China"}]}],"member":"1968","published-online":{"date-parts":[[2024,1,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"125","DOI":"10.3390\/drones7020125","article-title":"RSIn-Dataset: An UAV-Based Insulator Detection Aerial Images Dataset and Benchmark","volume":"7","author":"Feng","year":"2023","journal-title":"Drones"},{"key":"ref_2","first-page":"377","article-title":"Evaluation of the Severity of Discharge in Porcelain Suspension Insulator Based on Ultraviolet Imaging and Improved YOLOv3","volume":"47","author":"Law","year":"2021","journal-title":"High Volt. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"79945","DOI":"10.1109\/ACCESS.2019.2891123","article-title":"Insulator Detection in Aerial Images for Transmission Line Inspection Using Single Shot Multibox Detector","volume":"7","author":"Miao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1631\/jzus.A1900341","article-title":"Catenary insulator defect detection based on contour features and gray similarity matching","volume":"21","author":"Tan","year":"2020","journal-title":"J. Zhejiang Univ. Sci. A"},{"key":"ref_5","unstructured":"Liu, Y., Lu, Y.P., Gao, S., Bi, X.T., Yin, Q.G., Zhu, X.Q., and Yao, J.G. (2020). Application of Edge Detection in Infrared Images of Coil-type Suspension Porcelain Insulator. Electro-Ceram. Light. Prot., 198\u2013203. (In Chinese)."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1486","DOI":"10.1109\/TSMC.2018.2871750","article-title":"Detection of Power Line Insulator Defects Using Aerial Images Analyzed with Convolutional Neural Networks","volume":"50","author":"Tao","year":"2020","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"ref_7","unstructured":"Guo, J.N., Du, S.S., Wang, S.D., and Zhang, X.Y. (2022). CenterNet Self-Exploding Detection of Insulators on Transmission Lines Based on Lightweight Feature Fusion. J. Beijing Univ. Aeronaut. Astronaut., 1\u201313. (In Chinese)."},{"key":"ref_8","first-page":"294","article-title":"Lightweight Detection Method for Insulator Self-Explosion Defects in Aerial Photography","volume":"49","author":"Jia","year":"2023","journal-title":"High Volt. Technol."},{"key":"ref_9","first-page":"81","article-title":"Insulator Defect Detection Based on Multi-Scale Feature Coding and Dual Attention Fusion","volume":"59","author":"Li","year":"2022","journal-title":"Prog. Laser Photonics"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"012022","DOI":"10.1088\/1742-6596\/2560\/1\/012022","article-title":"Layout Optimization and Multi-scenes Intelligent Inspection Scheme Design Based on Substation Video Monitoring","volume":"2560","author":"Li","year":"2023","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"012013","DOI":"10.1088\/1742-6596\/2363\/1\/012013","article-title":"Detection of Defects in Power Grid Inspection Images Based on Multi-scale Fusion","volume":"2363","author":"Wu","year":"2022","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhao, H., Wan, F., Lei, G.B., Xiong, Y., Xu, L., Xu, C., and Zhou, W. (2023). LSD-YOLOv5: A Steel Strip Surface Defect Detection Algorithm Based on Lightweight Network and Enhanced Feature Fusion Mode. Sensors, 23.","DOI":"10.3390\/s23146558"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"110887","DOI":"10.1016\/j.knosys.2023.110887","article-title":"Lite-FENet: Lightweight multi-scale feature enrichment network for few-shot segmentation","volume":"278","author":"Li","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"ref_14","first-page":"101702","article-title":"Lightweight multi-level feature difference fusion network for RGB-D-T salient object detection","volume":"35","author":"Song","year":"2023","journal-title":"J. King Saud Univ.-Comput. Inf. Sci."},{"key":"ref_15","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume":"97","author":"Tan","year":"2019","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, B.R., He, K., Hariharan, B., and Belongie, S. (2017, January 21\u201326). Feature Pyramid Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"110005","DOI":"10.1016\/j.optlastec.2023.110005","article-title":"Classification and Recognition Method of Non-Cooperative Object Based on Transfer Learning","volume":"169","author":"Zhang","year":"2024","journal-title":"Opt. Laser Technol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ren, S.Q., He, K.M., Girshick, R., and Sun, J. (2017). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell., 39.","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"108166","DOI":"10.1016\/j.compag.2023.108166","article-title":"Flooding-based MobileNet to identify cucumber diseases from leaf images in natural scenes","volume":"213","author":"Liu","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"410","DOI":"10.2463\/mrms.mp.2020-0073","article-title":"Introducing Swish and Parallelized Blind Removal Improves the Performance of a Convolutional Neural Network in Denoising MR Images","volume":"20","author":"Taro","year":"2021","journal-title":"Magn. Reson. Med. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G., and Wu, E.H. (2019). Squeeze-and-Excitation Networks. IEEE Trans. Pattern Anal. Mach. Intell., 42.","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"055401","DOI":"10.1088\/1361-6501\/acb073","article-title":"A multiple feature-maps interaction pyramid network for defect detection of steel surface","volume":"34","author":"Zhao","year":"2023","journal-title":"Meas. Sci. Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"106433","DOI":"10.1016\/j.engappai.2023.106433","article-title":"A real-time mechanical fault diagnosis approach based on lightweight architecture search considering industrial edge deployments","volume":"123","author":"Ma","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"101793","DOI":"10.1016\/j.phycom.2022.101793","article-title":"Multi-task learning approach for modulation and wireless signal classification for 5G and beyond: Edge deployment via model compression","volume":"54","author":"Anu","year":"2022","journal-title":"Phys. Commun."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1219474","DOI":"10.3389\/fpls.2023.1219474","article-title":"Skip DETR: End-to-end Skip connection model for small object detection in forestry pest dataset","volume":"14","author":"Liu","year":"2023","journal-title":"Front. Plant Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Mirzaei, B., Nezamabadi-pour, H., Raoof, A., and Derakhshani, R. (2023). Small Object Detection and Tracking: A Comprehensive Review. Sensors, 23.","DOI":"10.3390\/s23156887"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 21\u201326). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Li, F.F. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 26th IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhang, H.P., Zhang, X.Y., Meng, G., Guo, C., and Jiang, Z. (2022). Few-Shot Multi-Class Ship Detection in Remote Sensing Images Using Attention Feature Map and Multi-Relation Detector. Remote Sens., 14.","DOI":"10.3390\/rs14122790"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1109\/TCYB.2022.3149825","article-title":"Decoupled Metric Network for Single-Stage Few-Shot Object Detection","volume":"53","author":"Lu","year":"2022","journal-title":"IEEE Trans. Cybern."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zou, L., Wang, K., Wang, X., Zhang, J., Li, R., and Wu, Z. (2023). Automatic Recognition Reading Method of Pointer Meter Based on YOLOv5-MR Model. Sensors, 23.","DOI":"10.3390\/s23146644"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/1\/290\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:39:03Z","timestamp":1760103543000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/1\/290"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,3]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["s24010290"],"URL":"https:\/\/doi.org\/10.3390\/s24010290","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,3]]}}}