Unmanned Aerial Vehicle (UAV) imagery, augmented by advanced deep learning architectures, has become an integral approach to the automated inspection and structural monitoring of high-voltage power grids. This study evaluates the practical applicability and speed-accuracy trade-offs of single-stage versus two-stage object detection models for identifying critical power grid components. Specifically, two highly optimized networks were developed and empirically validated: HVE-YOLO11, which uses the latest YOLO11 architecture enhanced with spatial attention mechanisms, and HVE-MASK-R-CNN, which uses a rigorous ResNet-101 Feature Pyramid Network (FPN) backbone. Leveraging a newly curated, diverse dataset of 51,800 augmented images capturing six distinct equipment classes under fluctuating meteorological conditions, the models were evaluated for Mean Average Precision (mAP) and computational throughput measured in Frames Per Second (FPS). Empirical results demonstrate that the single-stage HVE-YOLO11 shatters the traditional speed-accuracy dichotomy, significantly outperforming the two-stage model in both inference velocity (162.9 FPS versus 75.8 FPS in intensive benchmarking) and spatial accuracy (an mAP@0.5 of 0.972 compared to 0.855). These findings provide actionable, highly quantified benchmarks for deploying real-time, AI-driven diagnostic systems on hardware-constrained edge-computing UAV platforms.
References
Chen, W., Li, Y., & Li, C. (2020). A visual detection method for foreign objects in power lines based on Mask R-CNN. International Journal of Ambient Computing and Intelligence, 11(1), 34–47. https://doi.org/10.4018/IJACI.2020010103
Chen, X., Xu, X., Xue, J., Zhang, W., & Wang, Q. (2024). A scene knowledge integrating network for transmission line multi-fitting detection. Sensors, 24(24), Article 8207. https://doi.org/10.3390/s24248207
Faisal, M. A. A., Mecheter, I., Qiblawey, Y., Hernandez Fernandez, J., Chowdhury, M. E. H., & Kiranyaz, S. (2025). Deep learning in automated power line inspection: A review. Applied Energy, 385, Article 125507. https://doi.org/10.1016/j.apenergy.2025.125507
Ji, Y., Zhang, D., He, Y., Zhao, J., Dong, X., & Zhang, T. (2025). Improved YOLO11 algorithm for insulator defect detection in power distribution lines. Electronics, 14(6), Article 1201. https://doi.org/10.3390/electronics14061201
Rong, S., He, L., Atici, S. F., & Cetin, A. E. (2025). Advanced YOLO-based real-time power line detection for vegetation management. IEEE Transactions on Power Delivery, 40(4), 2142–2153. https://doi.org/10.48550/arXiv.2503.00044
Santos, T., Tiago, C., André, D., António, P. M., & José, A. (2024). UAV visual and thermographic power line detection using deep learning. Sensors, 24(17), Article 5678. https://doi.org/10.3390/s24175678
Shao, Y., Zhang, R., Lv, C., Luo, Z., & Che, M. (2024). TL-YOLO: Foreign-object detection on power transmission line based on improved YOLOv8. Electronics, 13(8), Article 1543. https://doi.org/10.3390/electronics13081543
Tang, K., Peng, Y., Wu, X., & Qi, L. (2025). Improvement of Mask R-CNN algorithm for ore segmentation. Electronics, 14(10), Article 2025. https://doi.org/10.3390/electronics14102025
Vemula, S., & Frye, M. (2020). Mask R-CNN powerline detector: A deep learning approach with applications to a UAV. In Proceedings of the 2020 IEEE/AIAA 39th Digital Avionics Systems Conference (DASC) (pp. 1–6). IEEE. https://doi.org/10.1109/DASC50938.2020.9256456
Wang, C., Chen, Y., Wang, Z., Li, B., Tang, H., Jiang, D., & Sui, X. (2025). Line-YOLO: An efficient detection algorithm for power line angle. Sensors, 25(3), Article 876. https://doi.org/10.3390/s25030876
Wang, Z., Yuan, G., Zhou, H., Ma, Y., & Ma, Y. (2023). Foreign-object detection in high-voltage transmission line based on improved YOLOv8m. Applied Sciences, 13(23), Article 12775. https://doi.org/10.3390/app132312775
Wang, Z., Yuan, G., Zhou, H., Ma, Y., Ma, Y., & Chen, D. (2025). Improved YOLOv7 model for insulator defect detection. arXiv. https://doi.org/10.48550/arXiv.2502.07179
Wu, X., Sahoo, D., & Hoi, S. C. H. (2020). Recent advances in deep learning for object detection. Neurocomputing, 396, 39–64. https://doi.org/10.1016/j.neucom.2020.01.085
Xu, J., Zhang, S., Liu, Y., Sun, W., & Zhang, K. (2025). MRB-YOLOv8: An algorithm for insulator defect detection. Electronics, 14(5), Article 830. https://doi.org/10.3390/electronics14050830
Zhou, M., Wang, J., & Liu, B. (2022). ARG-Mask RCNN: An infrared insulator fault-detection network based on improved Mask RCNN. Sensors, 22(13), Article 4720. https://doi.org/10.3390/s22134720