The week's pick
Reseach Article
Automatic PPE Monitoring System for Construction Workers using YOLO Algorithm based on Deep Reinforcement Learning
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 186 - Number 48 |
| Year of Publication: 2024 |
| Authors: Dominic Ocharo, H. Chege Nganga, Stephen Kiambi |
10.5120/ijca2024924094
|
Dominic Ocharo, H. Chege Nganga, Stephen Kiambi . Automatic PPE Monitoring System for Construction Workers using YOLO Algorithm based on Deep Reinforcement Learning. International Journal of Computer Applications. 186, 48 ( Nov 2024), 10-15. DOI=10.5120/ijca2024924094
Abstract
This paper describes an innovative system designed to detect and monitor the compliance of Personal Protective Equipment (PPE) usage within construction sites. A deep learning model is trained using the You Only Look Once (YOLO) algorithm and deployed on an IoT device to monitor employees on construction sites continuously. By seamlessly integrating advanced technologies such as deep learning methodologies, Bluetooth Low Energy (BLE) tags, Global Positioning System (GPS) modules, Fitbit devices, cameras, and sophisticated image processing algorithms, the system ensures the proper utilization of essential PPE items including safety helmets, vests, goggles, safety mask, and boots. Utilizing the different sensors affixed to PPE items and IoT devices, the system continuously emits signals for instant identification of compliance or non-compliance instances, while leveraging state-of-the-art image recognition techniques coupled with a convolutional neural network (CNN) to accurately discern PPE usage, ensuring compliance while on site. The system's efficacy was assessed based on precision, recall, and mean Average Precision (mAP) metrics, which confirmed its reliability and effectiveness in real-world operational environments. This comprehensive approach to PPE compliance monitoring signifies a significant advancement in ensuring workplace safety standards within construction sites, thereby contributing to the protection and well-being of workers in hazardous environments.
References
- Z. Wang, Y. Wu, L. Yang, A. Thirunavukarasu, C. Evison, and Y. Zhao, “Fast Personal Protective Equipment Detection for Real Construction Sites Using Deep Learning Approaches”, Sensors, vol. 21, pp. 3478, (2021).
- Y. Shim, “Comparative Analysis of Fatalities Per 100,000 Workers in the Construction Industry Among Developed Countriesusing Multi-Criteria Evaluation”, (2024).
- A. Hayat and F. Morgado-Dias, “Deep Learning-Based Automatic Safety Helmet Detection System for Construction Safety”, Applied Sciences, vol. 12, no. 16, pp. 8268, (2022).
- H. Zhang, X. Yan, H. Li, R. Jin, and H. Fu, “Real-Time Alarming, Monitoring, and Locating for Non-Hard-Hat Use in Construction”, Journal of Construction Engineering and Management, vol. 145, no. 3, pp. 04019006, (2019).
- N. D. Nath and A. H. Behzadan, “Deep Learning Detection of Personal Protective Equipment to Maintain Safety Compliance on Construction Sites”, Nov. 2020.
- S. Márquez-Sánchez, I. Campero-Jurado, J. Herrera-Santos, S. Rodríguez, and J. M. Corchado, “Intelligent Platform Based on Smart PPE for Safety in Workplaces”, Sensors, vol. 21, no. 14, pp. 4652, (2021).
- J. Seo, S. Han, S. Lee, and H. Kim, “Computer vision techniques for construction safety and health monitoring”, Advanced Engineering Informatics, vol. 29, no. 2, pp. 239–251, (2015).
- A. Kelm et al., “Mobile passive Radio Frequency Identification (RFID) portal for automated and rapid control of Personal Protective Equipment (PPE) on construction sites”, Automation in Construction, vol. 36, (2013).
- K.-J. Park, R. Zheng, and X. Liu, “Cyber-physical systems: Milestones and research challenges,” Computer Communications, vol. 36, no. 1, pp. 1–7, (2012).
- Z. Jiang and J. I. Messner, “Computer Vision-Based Methods Applied to Construction Processes: A Literature Review”, Construction Research Congress 2020, (2020).
- A. Kumar, Z. J. Zhang, and H. Lyu, “Object detection in real-time based on improved single shot multi-box detector algorithm”, EURASIP Journal on Wireless Communications and Networking, vol. 2020, no. 1, (2020).
- Y. Yin, H. Li, and W. Fu, “Faster-YOLO: An accurate and faster object detection method”, Digital Signal Processing, vol. 102, pp. 102756, (2020).
- A. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection”, Cv-foundation.org, pp. 779–788, (2016).
- A. S. Chen and K. Demachi, “A Vision-Based Approach for Ensuring Proper Use of Personal Protective Equipment (PPE) in Decommissioning of Fukushima Daiichi Nuclear Power Station”, Applied Sciences, vol. 10, no. 15, pp. 5129, (2020).
- A. J. Wu, N. Cai, W. Chen, H. Wang, and G. Wang, “Automatic detection of hardhats worn by construction personnel: A deep learning approach and benchmark dataset”, Automation in Construction, vol. 106, pp. 102894, (2019).
- A. S. Chi, C. H. Caldas, and D. Y. Kim, “A Methodology for Object Identification and Tracking in Construction Based on Spatial Modeling and Image Matching Techniques,” Computer-Aided Civil and Infrastructure Engineering, vol. 24, no. 3, pp. 199–211, (2009).
- A. S. Zhang, J. Teizer, N. Pradhananga, and C. M. Eastman, “Workforce location tracking to model, visualize and analyze workspace requirements in building information models for construction safety planning,” Automation in Construction, vol. 60, pp. 74–86, (2015).
Index Terms
Keywords