{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T05:01:11Z","timestamp":1790226071612,"version":"4.1.0"},"reference-count":27,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Small defect targets and complex backgrounds in transmission-line inspection images can limit detection accuracy, and existing detection models often incur substantial computational cost. To address these issues, this study proposes a cable defect detection method based on an improved RT-DETR. First, a DualConv module is introduced into the backbone to strengthen local feature representation while reducing parameter redundancy. Second, a ContextGuidedDown module is incorporated for downsampling to alleviate the loss of critical information. Finally, Dynamic Tanh replaces LayerNorm in the attention-based intra-scale feature interaction (AIFI) encoder to improve the regulation of high-level features. Experiments were conducted on the CableInspect-AD dataset and the RF100 Cable Damage dataset. In the main single-run comparison on CableInspect-AD, the proposed method achieves an mAP@0.5 of 92.4%, which is 2.7 percentage points higher than that of the original RT-DETR, while the number of parameters is reduced from 20.1 M to 18.6 M and the computational cost decreases from 58.3 to 53.4 GFLOPs. Across four paired random-seed runs, DCGD-RTDETR achieves a mean mAP@0.5 of 92.05 \u00b1 0.34%, compared with 90.98 \u00b1 1.10% for RT-DETR; however, the paired difference is not statistically significant (p = 0.086). In the same repeated-run analysis, AP@0.75 decreases from 65.01 \u00b1 1.43% for RT-DETR to 63.26 \u00b1 1.11% for DCGD-RTDETR (p = 0.005), indicating that localization performance at a stricter IoU threshold remains a limitation. Ablation experiments further confirm the complementary contributions of the three modifications. Overall, the proposed method provides a favorable detection-accuracy and model-complexity trade-off at IoU = 0.5, while further improvement is needed for stricter-IoU localization performance.<\/jats:p>","DOI":"10.3390\/s26196006","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T15:28:43Z","timestamp":1790090923000},"page":"6006","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cable Defect Detection Using an Improved RT-DETR Model"],"prefix":"10.3390","volume":"26","author":[{"given":"Ziwei","family":"Yi","sequence":"first","affiliation":[{"name":"School of Computer Science, Yangtze University, Jingzhou 434023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Yangtze University, Jingzhou 434023, China"},{"name":"Research Center for Digital Agriculture and Intelligent Engineering, Yangtze University, Jingzhou 434023, China"},{"name":"Artificial Intelligence Research Platform, Yangtze University, Jingzhou 434023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Yangtze University, Jingzhou 434023, China"},{"name":"Research Center for Digital Agriculture and Intelligent Engineering, Yangtze University, Jingzhou 434023, China"},{"name":"Artificial Intelligence Research Platform, Yangtze University, Jingzhou 434023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongxi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Yangtze University, Jingzhou 434023, China"},{"name":"Research Center for Digital Agriculture and Intelligent Engineering, Yangtze University, Jingzhou 434023, China"},{"name":"Artificial Intelligence Research Platform, Yangtze University, Jingzhou 434023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"ref_1","first-page":"180","article-title":"Review of Power Cable On-line Monitoring and Condition Assessment Technology","volume":"44","author":"Shan","year":"2025","journal-title":"Electr. Eng."},{"key":"ref_2","first-page":"1","article-title":"A review of diagnostic testing techniques for electrical power cables","volume":"68","author":"Gao","year":"2025","journal-title":"Wire Cable"},{"key":"ref_3","first-page":"972","article-title":"Detection Method of Partial Discharge Defects in Cable Terminals Based on Ultrasonic Infrared Thermography","volume":"44","author":"Deng","year":"2022","journal-title":"Infrared Technol."},{"key":"ref_4","first-page":"24","article-title":"Alternating current field measurement for lead seal defects of high-voltage cable accessories","volume":"44","author":"Liu","year":"2022","journal-title":"Nondestruct. Test."},{"key":"ref_5","first-page":"3009","article-title":"Research on Cable Local Defect Detection Method Based on Phase-Sensitive Characteristics of Frequency Modulated Continuous Wave","volume":"38","author":"Zhao","year":"2023","journal-title":"Trans. China Electrotech. Soc."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Li, J., Feng, Y.Q., Shao, Y.H., and Liu, F. (2024). IDP-YOLOV9: Improvement of Object Detection Model in Severe Weather Scenarios from Drone Perspective. Appl. Sci., 14.","DOI":"10.3390\/app14125277"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wang, Z.Y., Yuan, G.W., Zhou, H., Ma, Y., and Ma, Y.T. (2023). Foreign-Object Detection in High-Voltage Transmission Line Based on Improved YOLOv8m. Appl. Sci., 13.","DOI":"10.3390\/app132312775"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"10215","DOI":"10.1109\/JSEN.2023.3260360","article-title":"UAV High-Voltage Power Transmission Line Autonomous Correction Inspection System Based on Object Detection","volume":"23","author":"Li","year":"2023","journal-title":"IEEE Sens. J."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/s11554-024-01495-9","article-title":"Deep-learning-based insulator fault detection algorithm for power transmission lines","volume":"21","author":"Wang","year":"2024","journal-title":"J. Real-Time Image Process."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1007\/s42835-023-01625-6","article-title":"High-voltage transmission-line foreign-object and power-component defect detection based on improved YOLOv5","volume":"19","author":"Wang","year":"2024","journal-title":"J. Electr. Eng. Technol."},{"key":"ref_11","first-page":"2269","article-title":"Research on defect detection algorithm for high-voltage transmission line based on improved YOLOv9","volume":"47","author":"Yang","year":"2025","journal-title":"Chin. J. Eng."},{"key":"ref_12","first-page":"1529","article-title":"A surface defect detection method of steel cables based on improved YOLOv10","volume":"37","author":"Liu","year":"2025","journal-title":"J. Iron Steel Res."},{"key":"ref_13","first-page":"103","article-title":"High-voltage cable surface defect detection based on a cross-scale feature-fusion CNN-Transformer network","volume":"37","author":"Wei","year":"2025","journal-title":"Proc. CSU-EPSA"},{"key":"ref_14","first-page":"1","article-title":"An Attention Mechanism Based AVOD Network for 3D Vehicle Detection","volume":"8","author":"Yuan","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"9676","DOI":"10.1109\/TCSVT.2026.3665871","article-title":"Reliable-Teacher: Uncertainty-Guided Collaborative Learning for Nighttime Object Detection","volume":"36","author":"Luo","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024, January 16\u201322). DETRs Beat YOLOs on Real-Time Object Detection. Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"9528","DOI":"10.1109\/TNNLS.2022.3151138","article-title":"DualConv: Dual Convolutional Kernels for Lightweight Deep Neural Networks","volume":"34","author":"Zhong","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.1109\/TIP.2020.3042065","article-title":"CGNet: A Light-Weight Context Guided Network for Semantic Segmentation","volume":"30","author":"Wu","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zhu, J., Chen, X., He, K., LeCun, Y., and Liu, Z. (2025, January 10\u201317). Transformers without Normalization. Proceedings of the 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.01388"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"64703","DOI":"10.52202\/079017-2064","article-title":"CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset","volume":"37","author":"Arodi","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_21","unstructured":"Ciaglia, F., Zuppichini, F.S., Guerrie, P., McQuade, M., and Solawetz, J. (2022). Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ding, X.H., Zhang, X.Y., Han, J.G., and Ding, G.G. (2021, January 20\u201325). Diverse Branch Block: Building a Convolution as an Inception-Like Unit. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01074"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chen, L.W., Gu, L., Li, L., Yan, C., and Fu, Y. (2025, January 10\u201317). Frequency Dynamic Convolution for Dense Image Prediction. Proceedings of the 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.02809"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"4404312","DOI":"10.1109\/TGRS.2023.3282048","article-title":"A Robust Feature Downsampling Module for Remote-Sensing Visual Tasks","volume":"61","author":"Lu","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"109819","DOI":"10.1016\/j.patcog.2023.109819","article-title":"Haar Wavelet Downsampling: A Simple but Effective Downsampling Module for Semantic Segmentation","volume":"143","author":"Xu","year":"2023","journal-title":"Pattern Recognit."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Xia, Z.F., Pan, X.R., Song, S.J., Li, L.E., and Huang, G. (2022, January 18\u201324). Vision Transformer with Deformable Attention. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Shi, D. (2024, January 16\u201322). TransNeXt: Robust Foveal Visual Perception for Vision Transformers. Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01683"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6006\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T04:25:39Z","timestamp":1790223939000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6006"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"references-count":27,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196006"],"URL":"https:\/\/doi.org\/10.3390\/s26196006","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]}}}