AI-Enabled Lightweight Video Stream Processing for Electric Shock Prevention Monitoring in Smart Grid Edge Scenarios
DOI:
https://doi.org/10.4108/ew.15089Keywords:
Smart grid, Energy Internet, electric shock prevention monitoring, AI-enabled edge computing, lightweight video stream processing, YOLOv8n, visual safety warningAbstract
INTRODUCTION: Real-time early warning of electric shock risks is urgently needed in edge scenarios of smart grids. Existing visual methods are still limited by scene adaptability, end-to-end lightweight design, and insufficient field verification.
Objective: The objective of the study is to propose a lightweight video stream processing algorithm for power operation sites, balancing accuracy, latency, and deployment efficiency on edge devices.
METHODS: A constrained multi-objective model prioritizing safety risks is constructed, integrating risk-weighted ROI extraction, adaptive inter-frame filtering, lightweight image enhancement, ROI-aware YOLOv8n, pruning, and pipelined inference.
RESULTS: Data analysis shows that the model has 2.86M parameters, 3.12 GFLOPs of computation, a mAP@0.5 of 93.27%, and a Jetson Nano speed of 31.4 fps. In substations, the average mAP@0.5 is 92.14%, the early warning latency is 126 ms, and the false negative rate in rain, fog, low light, and occlusion scenarios is approximately 1%.
CONCLUSION: This method reduces redundant computation while maintaining high accuracy and low latency, providing an edge-intelligent solution for electric shock protection in smart grids.
Downloads
References
[1] Chen S, Wang D, Zhang X, Shao B, Cao K, Li Z. A spatiotemporal analysis of personal casualty accidents in China’s electric power industry. Heliyon. 2024;10(13):e33855. doi: 10.1016/j.heliyon.2024.e33855.
[2] de Souza DF, Martins WA, Martinho E, Tatizawa H. Accidents leading to electrical shocks in Brazilian electric power distribution: An analysis. IEEE Ind Appl Mag. 2024;30(3):61–67. doi: 10.1109/MIAS.2023.3328507.
[3] Yin Y, Lin J, Sun N, Zhu Q, Zhang S, Zhang Y, et al. Method for detection of unsafe actions in power field based on edge computing architecture. J Cloud Comput. 2021;10:17. doi: 10.1186/s13677-021-00234-w.
[4] Zhao B, Lan H, Niu Z, Zhu H, Qian T, Tang W. Detection and location of safety protective wear in power substation operation using wear-enhanced YOLOv3 algorithm. IEEE Access. 2021;9:125540–125549. doi: 10.1109/ACCESS.2021.3104731.
[5] Chen B, Wang X, Bao Q, Jia B, Li X, Wang Y. An unsafe behavior detection method based on improved YOLO framework. Electronics. 2022;11(12):1912. doi: 10.3390/electronics11121912.
[6] Lema DG, Usamentiaga R, García DF. Low-cost system for real-time verification of personal protective equipment in industrial facilities using edge computing devices. J Real-Time Image Process. 2023;20(6):111. doi: 10.1007/s11554-023-01368-7.
[7] Chen Z, Ma C, Ren J, Hao F, Wang Z. Research on the identification method of safety wearing of electric power workers based on deep learning. Front Energy Res. 2023;10:1091322. doi: 10.3389/fenrg.2022.1091322.
[8] Fang J, Li X. Object detection related to irregular behaviors of substation personnel based on improved YOLOv4. Appl Sci. 2022;12(9):4301. doi: 10.3390/app12094301.
[9] Lin Z, Chen W, Su L, Chen Y, Li T. HS-YOLO: Small object detection for power operation scenarios. Appl Sci. 2023;13(19):11114. doi: 10.3390/app131911114.
[10] Long X, Zheng Z, Liu R, Cui W, Chi Y, Zhang H, et al. Cascaded feature enhancement network model for real-time video monitoring of power system. Energy Rep. 2021;7:8485–8492. doi: 10.1016/j.egyr.2021.05.046.
[11] Ali Z, Park U. Real-time safety monitoring vision system for linemen in buckets using spatio-temporal inference. Int J Control Autom Syst. 2021;19(1):505–520. doi: 10.1007/s12555-019-0546-y.
[12] Liu C, Zhang W, Xu W, Lu B, Li W, Zhao X. Substation inspection safety risk identification based on synthetic data and spatiotemporal action detection. Sensors. 2025;25(9):2720. doi: 10.3390/s25092720.
[13] Zhao M, Barati M. Substation safety awareness intelligent model: Fast personal protective equipment detection using GNN approach. IEEE Trans Ind Appl. 2023;59(3):3142–3150. doi: 10.1109/TIA.2023.3234515.
[14] Zhang H, Mu C, Ma X, Guo X, Hu C. MEAG-YOLO: A novel approach for the accurate detection of personal protective equipment in substations. Appl Sci. 2024;14(11):4766. doi: 10.3390/app14114766.
[15] Nguyen DC, Nguyen TC. AI-powered edge-based safety monitoring system for power transmission corridors: A case study in Vietnam. Comput Netw. 2026;275:111881. doi: 10.1016/j.comnet.2025.111881.
[16] Tao C, Wang C, Li T. Detection research of insulating gloves wearing status based on improved YOLOv8s algorithm. J Eng Appl Sci. 2024;71(1):126. doi: 10.1186/s44147-024-00458-y.
[17] Li J, Zhao X, Zhou G, Zhang M. Standardized use inspection of workers’ personal protective equipment based on deep learning. Saf Sci. 2022;150:105689. doi: 10.1016/j.ssci.2022.105689.
[18] Gallo G, Di Rienzo F, Garzelli F, Ducange P, Vallati C. A smart system for personal protective equipment detection in industrial environments based on deep learning at the edge. IEEE Access. 2022;10:110862–110878. doi: 10.1109/ACCESS.2022.3215148.
[19] Wang L, Wang B, Zhang J, Ma H, Luo P, Yin T. An intelligent detection method for approach distances of large construction equipment in substations. Electronics. 2023;12(16):3510. doi: 10.3390/electronics12163510.
[20] Ma B, Liang G, Rao Y, Guo W, Zheng W, Wang Q. Knowledge reasoning- and progressive distillation-integrated detection of electrical construction violations. Sensors. 2024;24(24):8216. doi: 10.3390/s24248216.
[21] Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design. In: Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2021 Jun 20–25; Nashville, TN, USA (virtual conference). p. 13708–13717. doi: 10.1109/CVPR46437.2021.01350.
[22] Choi K, Wi SM, Jung HG, Suhr JK. Simplification of deep neural network-based object detector for real-time edge computing. Sensors. 2023;23(7):3777. doi: 10.3390/s23073777.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Dainan Zhang, Xiaohiu Li, Zijian Chen, Canshu Qiu, Hui Xu, Long Chen
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
