Hazard Detect AI: An Intelligent PPE Compliance Detection System Using YOLOv8

The Hazard Detect AI system demonstrates the practical application of artificial intelligence and computer vision in enhancing workplace safety. By employing the YOLOv8 object detection model, the system can automatically identify safety vest compliance from workplace images and provide accurate detection results. The integration of the detection model with a web-based application enables users to perform safety inspections quickly and efficiently. This approach minimizes the dependence on manual supervision and supports continuous monitoring in industrial and construction environments.   The proposed framework contributes to improving workplace safety by enabling timely identification of safety violations and promoting compliance with safety regulations. Its ability to process visual data automatically helps reduce human error and increases the effectiveness of safety management practices. The experimental results indicate that deep learning-based detection systems can serve as reliable tools for automated workplace monitoring and hazard prevention.   Future developments may focus on expanding the system’s capabilities to support real-time video surveillance and continuous monitoring through CCTV cameras. The framework can also be enhanced to detect multiple types of Personal Protective Equipment (PPE), including helmets, gloves, safety shoes, and protective goggles. Such extensions would allow the system to provide a more comprehensive safety compliance solution.   Additional improvements may include the integration of alert and notification mechanisms, cloud-based deployment, and mobile application support for remote access. Continuous dataset expansion and model optimization can further improve detection accuracy and robustness. These enhancements will increase the scalability, accessibility, and practical usability of the system, making it suitable for a wider range of workplace safety applications.

1.  López, L., Suárez-Ramírez, J., Alemán-Flores, M., & Monzón, N., “Automated PPE Compliance Monitoring Using Deep Learning-Based Detection and Pose Estimation,” Sensors, 2025. 2.  Ejaz, U., Ramon, W., Jeol, P., & Blessing, M., “IoT-Based Hazard Detection and Worker Safety Monitoring,” Safety Science, 2025. 3.  Ahmad, H. M., & Rahimi, A., “SH17: A Dataset for Human Safety and PPE Detection in Manufacturing Industry,” Journal of Imaging, 2024. 4.  Han, D., Ying, C., Tian, Z., Dong, Y., Chen, L., Wu, X., & Jiang, Z., “YOLOv8s-SNC: An Improved Safety Helmet Detection Algorithm Based on YOLOv8,” Buildings, 2024. 5.  Wang, H., “Detection of Personal Protective Equipment Using an Anchor-Free Convolutional Neural Network,” International Journal of Advanced Computer Science and Applications, 2024. 6.  Salchow, C. E., & Sylligardos, C., “Personal Protective Equipment Detection on Embedded Devices,” Electronics, 2024. 7.  Ludwika, A. S., & Rifai, A. P., “Deep Learning for Detection of Proper PPE Utilization in Laboratory Environments,” Journal of Engineering Education, 2024. 8.  Shi, C., Zhu, D., Shen, J., Zheng, Y., & Zhou, C., “GBSG-YOLOv8n: Enhanced PPE Detection in Industrial Environments,” Electronics, 2023. 9.  Kovacs, T., “Personal Protective Equipment Detection Using YOLOv5,” Forensic Engineering, 2023. 10.                    Liang, H., Zhang, Z., Wu, C., Wang, Y. X., & Shi, J., “Construction Personal Protective Equipment Detection Using Multimodal Deep Learning Models,” Sensors, 2023.