Construction safety accidents have become increasingly frequent in recent years, leading to numerous casualties and substantial property losses. These incidents are often attributed to inadequate supervision on construction sites and workers’ low safety awareness. Traditional manual management methods, which are labor-intensive and resource-consuming, are no longer effective. Therefore, this study proposes a novel single-stage model based on YOLOv8s, designed for two primary purposes: detecting workers’ personal protective equipment and monitoring and recognizing when workers enter hazardous areas. The model provides real-time feedback on detection results to reduce the incidence of construction accidents. Additionally, a brief design for distance calculation was introduced. The model was trained for 200 iterations on a Roboflow dataset comprising 103,500 annotated images. Experimental results showed that YOLOv8s outperformed YOLOv8n, YOLOv5s, and YOLOv5n in detection performance, achieving a mean average precision with the intersection over union (IoU) threshold set to 50% (mAP50) of 84.0%, precision of 85.0%, and recall of 60.5% across 9 detection classes. By leveraging artificial intelligence technology, this study aims to offer an effective method for enhancing construction site safety, which can be further improved with additional images and a more robust network architecture.