Multi-Object Tracking and Detection of Power Grid Construction Workers Based on Pre-trained YOLOv11

Lingwen Meng; Guobang Ban; Jintong Ma; Jiangang Liu; Mingyong Xin

doi:10.46604/ijeti.2026.16292

Authors

Lingwen Meng Electric Power Research Institute of Guizhou Power Grid Co., Ltd., Guiyang, China
Guobang Ban Electric Power Research Institute of Guizhou Power Grid Co., Ltd., Guiyang, China
Jintong Ma Electric Power Research Institute of Guizhou Power Grid Co., Ltd., Guiyang, China
Jiangang Liu Electric Power Research Institute of Guizhou Power Grid Co., Ltd., Guiyang, China
Mingyong Xin Electric Power Research Institute of Guizhou Power Grid Co., Ltd., Guiyang, China

DOI:

https://doi.org/10.46604/ijeti.2026.16292

Keywords:

safety helmet detection, multi-object tracking, YOLOv11, power grid construction

Abstract

This study aims to develop a real-time safety equipment detection and multi-object tracking framework for power grid construction scenarios. To this end, a dedicated dataset, E-hat, is constructed by combining a public safety helmet dataset with newly collected images from real-world power grid construction environments. Based on a pretrained lightweight you only look once version (YOLOv11n) detector, this paper introduces scenario-oriented input enhancement strategies, including hue-saturation-value (HSV) perturbation, Mosaic augmentation, and Mixup augmentation, to improve robustness under complex lighting, dense background interference, and partial occlusion. In addition, the detector is integrated with the BoT-SORT algorithm to form a detection-tracking-warning pipeline for continuous worker monitoring, hazardous area intrusion recognition, and unsafe behavior warning. Experimental results show that the proposed system achieves 92.7% precision, 93.4% mAP@0.5, and 183 frames per second (FPS) on the E-hat dataset. Real-world video tests further demonstrate multiple object tracking accuracy (MOTA) values up to 97.71%, demonstrating its practical potential in power safety management.

References

M. K. Mahadi, R. Rahad, M. S. Mobassir, A. Rahman, A. Shafiullah, and M. M. Nishat, "Implementation of Personal Safety Equipment Tracking & Detection by Deepsort & Yolov8," Proceedings of 2024 International Conference on Inventive Computation Technologies (ICICT), IEEE, pp. 1969-1974, 2024.

S. Rasouli, Y. Alipouri, and S. Chamanzad. "Smart Personal Protective Equipment (PPE) for Construction Safety: A Literature Review," Safety Science, vol. 170, article no. 106368, 2024.

R. Yamaguchi, Y. Makino, S. Torimitsu, G. Inokuchi, F. Chiba, M. Yoshida, et al., "Occupational Accidental Injury Deaths in Tokyo and Chiba Prefectures, Japan: A 10‐Year Study (2011–2020) of Forensic Institute Evaluations," Journal of Forensic Sciences vol. 68, no. 1, pp. 185-197, 2023.

M. Çiftçi, M. U. Türkdamar, and C. Öztürk. "Leveraging Yolo Models for Safety Equipment Detection on Construction Sites," Journal of Computing Theories and Applications, vol. 1, no. 4, pp. 492-506, 2024.

H. Wang, G. Wang, D. Lou, Y. Liu, L. Zhang and J. J. Fu, "Research on Power Scene Abnormal Recognition Technology Based on AI Edge Depth Algorithm Video Analysis Device," Power Systems and Big Data, vol. 24, no. 11, pp. 1-8, 2021.

B. Liu, W. Zhao, and Q. Sun, "Study of Object Detection Based on Faster R-CNN," Proceedings of 2017 Chinese automation congress (CAC), IEEE, pp. 6233-6236, 2017.

Sumit, B. Sumit, S. Joshi, and U. Rana. "Comprehensive Review of R-CNN and Its Variant Architectures," International Research Journal on Advanced Engineering Hub, vol. 2, no. 04, pp. 959-966, 2024.

S. Chen, W. Tang, T. Ji, H. Zhu, Y. Ouyang, and W. Wang, "Detection of Safety Helmet Wearing Based on Improved Faster R-CNN," Proceedings of 2020 International joint conference on neural networks (IJCNN), IEEE, pp. 1-7, 2020.

T. YaJie and P. Lian, "Improved Lightweight Helmet Wearing Detection Method for Yoloxs," Proceedings of 2022 China Automation Congress (CAC), IEEE, pp. 737-741, 2022.

J. Deng, X. Xuan, W. Wang, Z. Li, H. Yao, and Z. Wang, "A Review of Research on Object Detection Based on Deep Learning," Journal of physics: Conference series, vol. 1684, no. 1, article no. 012028, 2020.

W. Xu, Y. Zhao, X. Du, H. Ji, and L. Xing. "A Study on Bus Passenger Boarding and Alighting Detection and Recognition Based on Video Images and Yolo Algorithm," Sensors, vol. 26, no. 5, article no. 1418, 2026.

F. Zhou, H. Zhao, and Z. Nie, "Safety Helmet Detection Based on Yolov5," Proceedings of 2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA), IEEE, pp. 6-11, 2021.

S. Tan, G. Lu, Z. Jiang, and L. Huang, "Improved Yolov5 Network Model and Application in Safety Helmet Detection," Proceedings of 2021 IEEE International Conference on Intelligence and Safety for Robotics (ISR), IEEE, pp. 330-333, 2021.

Y. Jiang, S. Guo, L. Li, Z. Sheng, X. Song, and Y. Wei, "Research on Self Inspection Algorithm of Field Operation Based on Improved Yolov8n," Proceedings of 2025 4th International Symposium on Robotics, Artificial Intelligence and Information Engineering (RAIIE), pp. 60-66, 2025.

B. Lin. "Safety Helmet Detection Based on Improved Yolov8," IEEE Access, vol. 12, pp. 28260-28272, 2024.

L.-h. He, Y.-z. Zhou, L. Liu, W. Cao, and J.-h. Ma. "Research on Object Detection and Recognition in Remote Sensing Images Based on Yolov11," Scientific Reports, vol. 15, no. 1, article no. 14032, 2025.

X. He, X. Chen, X. Du, X. Wang, S. Xu, and J. Guan. "Maritime Target Radar Detection and Tracking via DTNet Transfer Learning Using Multi-Frame Images," Remote Sensing, vol. 17, no. 5, article no. 836, 2025.

L. Huang, Q. Fu, M. He, D. Jiang, and Z. Hao. "Detection Algorithm of Safety Helmet Wearing Based on Deep Learning," Concurrency and Computation: Practice and Experience, vol. 33, no. 13, article no. e6234, 2021.