Hardhat-wearing detection based on YOLOv5 in Internet-of-Things
Abstract
Worker safety is paramount in many industries. An essential component of industrial safety protocols involves the proper use of hardhats. However, due to lax safety awareness, many workers neglect to wear hardhats correctly, leading to frequent on-site accidents in China. Traditional detection methods, such as manual inspection and video surveillance, are inefficient and costly. Real-time monitoring of hardhat use is vital to boost compliance with hardhat usage and decrease accident rates. Recently, the advancement of the Internet of Things (IoT) and edge computing has provided an opportunity to improve these methods. In this study, two detection models based on You Only Look Once (YOLO) v5, hardhat-YOLOv5s and hardhat-YOLOv5n, were designed, validated, and implemented, tailored for hardhat detection. First, a public hardhat dataset was enriched to bolster the detection model’s robustness. Then, hardhat detection models were trained using the YOLOv5s and YOLOv5n, each catering to edge computing terminals with varying performance capacities. Finally, the models were validated using image and video data. The experimental results indicated that both models provided high detection precision and satisfied practical application needs. On the augmented public dataset, the hardhat-YOLOv5s and hardhat-YOLOv5n models have a Mean Average Precision (mAP) of 87.9% and 85.5%, respectively, for all six classes. Compared with the hardhat-YOLOv5s model, Parameters and Giga Floating-point Operations (GFLOPs) of the hardhat-YOLOv5n model decrease by 74.8% and 73.4%, respectively, and Frame per Second (FPS) increases by 30.5% on the validation dataset, which is more suitable for low-cost edge computing terminals with less computational power.
Keywords
Full Text:
PDFReferences
1. Chen Z, Su M. Improved mask R-CNN method for intelligent monitoring of helmet in power plant. In: Proceedings of the Photonics & Electromagnetics Research Symposium; 22 November 2021; Hangzhou, China.
2. Yang B, Qin H, Xie H, et al. Helmet detection under the power construction scene based on image analysis. In: Proceedings of the IEEE 7th International Conference on Computer Science and Network Technology; 19–20 October 2019; Dalian, China.
3. Chang X, Liu X. Fault tree analysis of unreasonably wearing helmets for builders. Journal of Jilin Jianzhu University 2018; 35(6): 65–69.
4. Zheng H. Research on Video Recognition of Safety Protection Measures for Electric Power Construction Personnel [Master’s thesis]. Guangdong University of Technology; 2021.
5. Liang W, Jing Z, Zhou Z, et al. Research on detection algorithm of helmet wearing state in electric construction. In: Proceedings of the 14th National Academic Conference on Signal and Intelligent Information Processing and Application; 11 April 2021; Beijing, China.
6. Sun C, Wang Y, Zhao J. Research on online detection technology of construction workers’ hardhats. Science and Technology and Innovation 2021; 19: 85–86.
7. Xu S, Wang Y, Gu Y. Construction site safety helmet wearing detection based on improved region convolutional neural network. Computer Engineering and Design 2020; 4(5): 1385–1389.
8. Lv M. Analyzing the monitoring technology of helmet wearing on construction site. Low Carbon Word 2018; 7: 205–206.
9. Liao M, Dan W, Lai Q. The communication structure of integrated automation system in 220KV conventional substation. Electric Engineering 2018; 7: 76–78.
10. Wang Y, Su B, Zhao H. The concept and development trend of power Internet of Things (Chinese). Telecommunications Science 2010; 26(S3): 9–14.
11. Shi W, Cao J, Zhang Q et al. Edge computing: vision and challenges. IEEE Internet of Things Journal 2016; 3(5): 637–646.
12. Wang S, Zafer M, Leung KK. Online placement of multi-component applications in edge computing environments. IEEE Access 2017; 5: 2514–2533.
13. Shi W, Sun H, Cao J. Edge computing—An emerging computing model for the Internet of Everything era. Journal of Computer Research and Development 2017; 54(5): 907–924.
14. Nguyen HH, Ta TN, Nguyen NC, et al. YOLO Based Real-Time Human Detection for Smart Video Surveillance at the Edge. In: Proceedings of IEEE Eighth International Conference on Communications and Electronics (ICCE); 13 January 2021; Phu Quoc Island, Vietnam.
15. Feng H, Mu G, Zhong S, et al. Benchmark Analysis of YOLO Performance on Edge Intelligence Devices. Cryptography 2022; 6(2): 16.
16. Wu D, Wang H, Li J. Safety helmet detection and identification based on improved faster RCNN. Information Technology and Informatization 2020; 1: 17–20.
17. Wang B, Li WJ, Tang H. Improved YOLOv3 algorithm and its application in helmet detection. Computer Engineering and Applications 2020; 56(9): 33–40.
18. Ge Q, Zhang Z, Yuan L, et al. Safety helmet wearing detection method of fusing environmental features and improved YOLOv4. Journal of Image and Graphics 2021; 26(12): 2904–2917.
19. Redmon J, Divvala S, Girshick R, et al. You Only Look Once: Unified, Real-Time Object Detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 27–30 June 2016; Las Vegas, USA.
20. Safety Helmet Detection. Available online: https://www.kaggle.com/andrewmvd/hard-hat-detection (accessed on 24 September 2023).
DOI: https://doi.org/10.32629/jai.v7i2.1255
Refbacks
- There are currently no refbacks.
Copyright (c) 2023 Wanbo Luo, Rajeswari Raju, Khairul Khaizi Mohd Shariff, Ahmad Ihsan Mohd Yassin
License URL: https://creativecommons.org/licenses/by-nc/4.0/