Industries such as construction, cold food processing, and the chemical sector are particularly vulnerable to a range of potential hazards. Personal Protective Equipment (PPE) plays a critical role in safeguarding workers in these high-risk environments. However, ensuring the consistent use of PPE and adherence to established safety protocols is a complex task. This complexity arises from factors such as human error, negligence, and inadequate supervision. Traditional methods of monitoring PPE compliance typically involve manual inspections, which are not only labor-intensive but also have demonstrated limited effectiveness in ensuring consistent PPE use. To address these challenges, this study proposes the utilization of the YOLOv8 algorithm to achieve improved accuracy and suitability for a broader range of real-world working environments. In support of this approach, we have developed a new dataset named PPE-AYN, which includes five distinct classes (person, head, hat, glasses, and glove) and comprises a total of 2980 images. The YOLOv8 algorithm represents the latest advancement in the YOLO family of object detection models and is renowned for its rapid and precise detection capabilities. These characteristics make YOLOv8 particularly well-suited for the task of PPE detection, offering a promising solution to enhance safety compliance in various industrial settings. By leveraging this technology, we aim to significantly improve the monitoring and enforcement of PPE usage, thereby reducing the risk of accidents and injuries in hazardous work environments.
Le et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: