Construction sites are among the most hazardous working environments due to the frequent occurrence of accidents caused by improper use of Personal Protective Equipment (PPE). Manual monitoring of workers is labor-intensive, time-consuming, and prone to human error, making automated safety monitoring an essential requirement. This research proposes a real-time PPE detection system using the YOLO11 object detection algorithm to automatically identify workers and detect essential safety equipment such as helmets, safety vests, gloves, boots, and goggles. The proposed methodology begins with dataset collection, annotation validation, and class remapping to improve dataset consistency. A YOLO11s model is trained using transfer learning with data augmentation techniques to enhance detection accuracy under varying environmental conditions. The trained model is evaluated using standard object detection metrics including Precision, Recall, Intersection over Union (IoU), and mean Average Precision (mAP). Experimental results demonstrate that the proposed model accurately detects multiple PPE categories in real time while maintaining high inference speed suitable for industrial surveillance systems. The developed system reduces the dependency on manual supervision and provides continuous safety monitoring for construction environments. The proposed framework can be integrated with CCTV surveillance systems to automatically identify safety violations and generate alerts. The research contributes toward improving workplace safety, reducing accidents, and supporting intelligent construction site management through artificial intelligence and computer vision technologies.

Mohammed Arsath A, Yashika C K, Tharshini K, Thanishka, Dhanaya,"Real-Time AI-Based Personal Protective Equipment Detection and Safety Compliance Monitoring for Construction Sites Using YOLO11" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(4): Page(546-553) July - August 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.