YOLOv10-MsA: Attention-Augmented Real-Time Insulator Defect Detection from UAV Imagery
Downloads
The reliable operation of transmission systems depends on early detection of defects within high-voltage insulators because it helps stop power outages. Scalable inspection remains a challenge since UAV-based imagery and deep learning generate recent promising solutions. The goal of this study is to build an accurate and time-efficient insulator defect detection system through the YOLOv10 architecture integration of Manhattan Self-Attention (MsA), which strengthens spatial feature detection and increases robustness during evaluations in complex aerial inspection scenarios. The designers implemented the MsA modules into the backbone and neck sections of YOLOv10 to develop YOLOv10-MsA as their novel detection model. The model relied on 5,000 annotated insulator images acquired by unmanned aerial vehicles throughout various defect classes during training and evaluation. Standard object detection metrics consisting of mAP@0.5, mAP@0.5:0.95, precision, recall, F1-score, and inference speed evaluated the performance of the model. The YOLOv10-MsA system reached an mAP@0.5 performance of 93.1% and an F1-score of 91.9% at an inference speed of 79 FPS, which surpasses YOLOv8, YOLOv9, and baseline YOLOv10. The model demonstrated its best performance at detecting various small and hard-to-detect defects such as chipping and contamination. The application of MsA in detection systems resulted in better accuracy while preserving real-time operation, according to related model assessment. The proposed YOLOv10-MsA serves as a powerful deployable system for UAV-based insulator inspection because it achieves both high accuracy and fast operation. The method establishes conditions for real-time smart infrastructure observation with attention-augmented frameworks for object detection.
Downloads
[1] Zhang, L., Li, B., Cui, Y., Lai, Y., & Gao, J. (2024). Research on improved YOLOv8 algorithm for insulator defect detection. Journal of Real-Time Image Processing, 21(1), 22. doi:10.1007/s11554-023-01401-9.
[2] Zheng, J., Wu, H., Zhang, H., Wang, Z., & Xu, W. (2022). Insulator-Defect Detection Algorithm Based on Improved YOLOv7. Sensors, 22(22), 8801. doi:10.3390/s22228801.
[3] Fahim, F., & Hasan, M. S. (2024). Enhancing the reliability of power grids: A YOLO based approach for insulator defect detection. E-Prime - Advances in Electrical Engineering, Electronics and Energy, 9, 100663. doi:10.1016/j.prime.2024.100663.
[4] Zhang, Y., Wu, Z., Wang, X., Fu, W., Ma, J., & Wang, G. (2023). Improved YOLOv8 Insulator Fault Detection Algorithm Based on BiFormer. 2023 IEEE 5th International Conference on Power, Intelligent Computing and Systems, ICPICS 2023, 962–965. doi:10.1109/ICPICS58376.2023.10235397.
[5] Liu, C., Yi, W., Liu, M., Wang, Y., Hu, S., & Wu, M. (2023). A Lightweight Network Based on Improved YOLOv5s for Insulator Defect Detection. Electronics (Switzerland), 12(20), 4292. doi:10.3390/electronics12204292.
[6] Ouyang, C., Zhang, H., Mu, X., Wu, Z., & Dai, W. (2023). E-VarifocalNet: A Lightweight Model to Detect Insulators and Their Defects under Power Grid Surveillance. 2023 IEEE 21st International Conference on Industrial Informatics (INDIN), 1–6. doi:10.1109/indin51400.2023.10217966.
[7] Liu, C., Wu, Y., Liu, J., Sun, Z., & Xu, H. (2021). Insulator faults detection in aerial images from high-voltage transmission lines based on deep learning model. Applied Sciences (Switzerland), 11(10), 4647. doi:10.3390/app11104647.
[8] He, M., Qin, L., Deng, X., & Liu, K. (2024). MFI-YOLO: Multi-Fault Insulator Detection Based on an Improved YOLOv8. IEEE Transactions on Power Delivery, 39(1), 168–179. doi:10.1109/TPWRD.2023.3328178.
[9] Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv Preprint, arXiv:1804.02767. doi:10.48550/arXiv.1804.02767.
[10] Gallagher, J. E., & Oughton, E. J. (2025). Surveying You Only Look Once (YOLO) Multispectral Object Detection Advancements, Applications, and Challenges. IEEE Access, 13, 7366–7395. doi:10.1109/ACCESS.2025.3526458.
[11] Hussain, M. (2024). Yolov5, Yolov8 and Yolov10: The go-to detectors for real-time vision. arXiv Preprint, arXiv:2407.02988. doi:10.48550/arXiv.2407.02988.
[12] Apak, S., & Farsadi, M. (2025). Multi-branch spatial pyramid dynamic graph convolutional neural networks for solar defect detection. Computers and Electrical Engineering, 121, 109872. doi:10.1016/j.compeleceng.2024.109872.
[13] Wu, T., Sha, T., Yao, X., Hu, J., Ma, Y., & Zhang, J. (2025). Improvement of the YOLO Series for Detecting Tower Cranes Based on High-Resolution Remote Sensing Imagery. Journal of Geovisualization and Spatial Analysis, 9(1), 8. doi:10.1007/s41651-024-00208-x.
[14] Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). CBAM: Convolutional Block Attention Module. Computer Vision – ECCV 2018. ECCV 2018, Lecture Notes in Computer Science, Springer, Cham, Switzerland. doi:10.1007/978-3-030-01234-2_1.
[15] Zhao, X., Wang, L., Zhang, Y., Han, X., Deveci, M., & Parmar, M. (2024). A review of convolutional neural networks in computer vision. Artificial Intelligence Review, 57(4), 99. doi:10.1007/s10462-024-10721-6.
[16] Feng, C., Cao, Z., Xiao, Y., Fang, Z., & Zhou, J. T. (2023). Multi-spectral template matching based object detection in a few-shot learning manner. Information Sciences, 624, 20–36. doi:10.1016/j.ins.2022.12.067.
[17] Qi, M., Tang, R., Liu, Z., Fu, S. (2024). AYOLOv8: Improved Detector Based on YOLOv8 to Focus More on Small and Medium Objects. Advanced Intelligent Computing Technology and Applications. ICIC 2024, Lecture Notes in Computer Science, Springer, Singapore. doi:10.1007/978-981-97-5594-3_8.
[18] Adou, M. W., Xu, H., & Chen, G. (2019). Insulator Faults Detection Based on Deep Learning. 2019 IEEE 13th International Conference on Anti-Counterfeiting, Security, and Identification (ASID), 173–177. doi:10.1109/icasid.2019.8925094.
[19] Cheng, Y. (2022). Detection of Power Line Insulator Based on Enhanced YOLO Model. 2022 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC), 626–632. doi:10.1109/ipec54454.2022.9777398.
[20] Guo, F., Hao, K., Xia, M., Zhao, L., Wang, L., & Liu, Q. (2019). Detection of Insulator Defects Based on YOLO V3.Artificial Intelligence for Communications and Networks. AICON 2019, Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, Springer, Cham, Switzerland. doi:10.1007/978-3-030-22971-9_25.
[21] Liu, X., Miao, X., Jiang, H., & Chen, J. (2020). Data analysis in visual power line inspection: An in-depth review of deep learning for component detection and fault diagnosis. Annual Reviews in Control, 50, 253–277. doi:10.1016/j.arcontrol.2020.09.002.
[22] Karthik, A., Kumar Sahoo, S., Kumar, A., Patel, N., Chinnaraj, P., Phaneendra Maguluri, L., Shuaib, M., & Rajaram, A. (2025). Unified approach for accurate brain tumor Multi-Classification and segmentation through fusion of advanced methodologies. Biomedical Signal Processing and Control, 100, 106872. doi:10.1016/j.bspc.2024.106872.
[23] Khanam, R., Hussain, M., Hill, R., & Allen, P. (2024). A Comprehensive Review of Convolutional Neural Networks for Defect Detection in Industrial Applications. IEEE Access, 12, 94250–94295. doi:10.1109/ACCESS.2024.3425166.
[24] Hassan, W., Hussain, G. A., Wahid, A., Safdar, M., Khalid, H. M., & Jamil, M. K. M. (2024). Optimum feature selection for classification of PD signals produced by multiple insulation defects in electric motors. Scientific Reports, 14(1), 23446. doi:10.1038/s41598-024-73196-z.
[25] Deng, J., Dong, W., Socher, R., Li, L.-J., Kai Li, & Li Fei-Fei. (2009). ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 248–255. doi:10.1109/cvpr.2009.5206848.
[26] Finlayson, M. A., & Erjavec, T. (2017). Overview of Annotation Creation: Processes and Tools. Handbook of Linguistic Annotation. Springer, Dordrecht, Netherlands. doi:10.1007/978-94-024-0881-2_5.
[27] Dang, F., Chen, D., Lu, Y., & Li, Z. (2023). YOLOWeeds: A novel benchmark of YOLO object detectors for multi-class weed detection in cotton production systems. Computers and Electronics in Agriculture, 205, 107655. doi:10.1016/j.compag.2023.107655.
[28] Su, J., Yuan, Y., Przystupa, K., & Kochan, O. (2024). Insulator defect detection algorithm based on improved YOLOv8 for electric power. Signal, Image and Video Processing, 18(8–9), 6197–6209. doi:10.1007/s11760-024-03307-w.
[29] Arifando, R., Eto, S., Tibyani, T., & Wada, C. (2025). Improved YOLOv10 for Visually Impaired: Balancing Model Accuracy and Efficiency in the Case of Public Transportation. Informatics, 12(1), 7. doi:10.3390/informatics12010007.
[30] Terven, J., Córdova-Esparza, D. M., & Romero-González, J. A. (2023). A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, 5(4), 1680–1716. doi:10.3390/make5040083.
[31] Panigrahy, S., & Karmakar, S. (2024). Real-Time Condition Monitoring of Transmission Line Insulators Using the YOLO Object Detection Model with a UAV. IEEE Transactions on Instrumentation and Measurement, 73, 1–9. doi:10.1109/TIM.2024.3381693.
[32] He, K., Gkioxari, G., Dollar, P., & Girshick, R., (2017). Mask, R-CNN. Computer vision (ICCV). Proceedings of the IEEE International Conference on Computer Vision (ICCV), 22-29 October, 2017, Venice, Italy.
[33] Ren, S., He, K., Girshick, R., & Sun, J. (2017). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137–1149. doi;10.1109/tpami.2016.2577031.
[34] Heuillet, A., Nasser, A., Arioui, H., & Tabia, H. (2024). Efficient Automation of Neural Network Design: A Survey on Differentiable Neural Architecture Search. ACM Computing Surveys, 56(11), 1–36. doi:10.1145/3665138.
[35] Hu, D., Yu, M., Wu, X., Hu, J., Sheng, Y., Jiang, Y., Huang, C., & Zheng, Y. (2024). DGW-YOLOv8: A small insulator target detection algorithm based on deformable attention backbone and WIoU loss function. IET Image Processing, 18(4), 1096–1108. doi:10.1049/ipr2.13009.
[36] Li, Z., Jiang, C., & Li, Z. (2024). An Insulator Location and Defect Detection Method Based on Improved YOLOv8. IEEE Access, 12, 106781–106792. doi:10.1109/access.2024.3436919.
[37] Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., Duerig, T., & Ferrari, V. (2020). The Open Images Dataset V4: Unified Image Classification, Object Detection, and Visual Relationship Detection at Scale. International Journal of Computer Vision, 128(7), 1956–1981. doi:10.1007/s11263-020-01316-z.
[38] Mumuni, F., & Mumuni, A. (2024). Segment Anything Model for automated image data annotation: empirical studies using text prompts from Grounding DINO. arXiv Preprint, arXiv:2406.19057. doi:10.48550/arXiv.2406.19057.
[39] Rizk, M., & Bayad, I. (2025). Bringing Intelligence to SAR Missions: A Comprehensive Dataset and Evaluation of YOLO for Human Detection in TIR Images. IEEE Access, 13, 17208–17235. doi:10.1109/ACCESS.2025.3529484.
[40] Lu, D., & Wang, Y. (2024). MAR-YOLOv9: A multi-dataset object detection method for agricultural fields based on YOLOv9. PLOS ONE, 19(10), e0307643. doi:10.1371/journal.pone.0307643.
[41] Liu, D. (2024). Study on insulator defect detection based on improved YOLOv8. Journal of Physics: Conference Series, 2770(1), 012009. doi:10.1088/1742-6596/2770/1/012009.
[42] Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., & Ren, D. (2020). Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. Proceedings of the AAAI Conference on Artificial Intelligence, 34(7), 12993–13000. doi:10.1609/aaai.v34i07.6999.
[43] Zhai, H., Cheng, J., & Wang, M. (2020). Rethink the IoU-based loss functions for bounding box regression. 2020 IEEE 9th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 1522–1528. doi:10.1109/itaic49862.2020.9339070.
[44] Zhang, Y. F., Ren, W., Zhang, Z., Jia, Z., Wang, L., & Tan, T. (2022). Focal and efficient IOU loss for accurate bounding box regression. Neurocomputing, 506, 146–157. doi:10.1016/j.neucom.2022.07.042.
[45] Cong, S., & Zhou, Y. (2023). A review of convolutional neural network architectures and their optimizations. Artificial Intelligence Review, 56(3), 1905–1969. doi:10.1007/s10462-022-10213-5.
[46] Saponara, S., Elhanashi, A. (2022). Impact of Image Resizing on Deep Learning Detectors for Training Time and Model Performance. Applications in Electronics Pervading Industry, Environment and Society, ApplePies 2021, Lecture Notes in Electrical Engineering, vol 866, Springer, Cham, Switzerland. doi:10.1007/978-3-030-95498-7_2.
[47] Song, Q., Zhou, Z. H., Ji, S. De, Cui, T., Yao, B. D., & Liu, Z. Q. (2024). A Multiscale Parallel Pedestrian Recognition Algorithm Based on YOLOv5. Electronics (Switzerland), 13(10), 1989. doi:10.3390/electronics13101989.
[48] Zan, W., Dong, C., Zhang, Z., Chen, X., Zhao, J., & Hao, F. (2023). Defect Identification of Power Line Insulators Based on a MobileViT-Yolo Deep Learning Algorithm. IEEJ Transactions on Electrical and Electronic Engineering, 18(8), 1271–1279. doi:10.1002/tee.23825.
[49] Souza, B. J., Stefenon, S. F., Singh, G., & Freire, R. Z. (2023). Hybrid-YOLO for classification of insulators defects in transmission lines based on UAV. International Journal of Electrical Power and Energy Systems, 148, 108982. doi:10.1016/j.ijepes.2023.108982.
[50] Wang, L., Qin, J., Yan, K., Sun, H., Sun, S., & Geng, Y. (2024). A Lightweight Insulator Defect Detection Model Based on YOLOv8. 2024 5th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT), 2349–2353. doi:10.1109/ainit61980.2024.10581815.
[51] Habib, G., & Qureshi, S. (2022). Optimization and acceleration of convolutional neural networks: A survey. Journal of King Saud University - Computer and Information Sciences, 34(7), 4244–4268. doi:10.1016/j.jksuci.2020.10.004.
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
