Construction safety remains a critical focus for both practitioners and researchers due to the sector’s high rates of accidents and fatalities. Among the most effective measures to mitigate these safety risks is the consistent use of personal protective equipment (PPE), which provides a vital defense against workplace hazards. However, ensuring compliance with PPE usage on dynamic construction sites is a persistent challenge. This research introduces several innovative models designed to enhance PPE compliance among construction workers. The study leverages convolutional neural networks (CNNs) and transfer learning principles to build upon the advanced YOLO-v5 and YOLO-v8 architectures. These models are specifically designed to predict six critical categories related to construction safety: person, vest, and four distinct helmet colors. Additionally, You only look once (YOLO) results were integrated with a safety Power BI dashboard providing stakeholders with a comprehensive overview of the site’s safety status, enabling them to monitor compliance trends and to take prompt corrective actions. Validation of the models was conducted using two datasets: (CHV benchmark dataset and an original dataset collected from Egyptian construction. YOLO-v5 × 6 model was noted for its superior speed in analysis compared to the YOLO-v5l model. However, the YOLO-v8m model outperformed all others in terms of precision and accuracy. Specifically, YOLO-v8m achieved the highest mean average precision (mAP) score of 92.30% and the best F1 score of 0.89. It can be argued that the developed model could significantly contribute to endorsing the ability to prevent accidents and improving safety measures in construction environment.
Elesawy et al. (Tue,) studied this question.