Scalable PPE Monitoring System Using Deep Object Detection Framework

The PPE Detection system is designed to automatically identify and classify personal protective equipment in images to ensure safety compliance in workplaces. The system leverages advanced deep learning models, including YOLOv26 and YOLOv12, to detect items such as helmets, masks, gloves, and safety vests. Images are preprocessed for consistency, and detection models are applied to locate and classify PPE objects. The backend, built using Python and Flask, manages user authentication, image processing, and model inference. The frontend, developed with HTML, CSS, and JavaScript, provides an interactive interface for image upload, detection, and visualization of results. Detected PPE items are displayed with bounding boxes and confidence scores, allowing users to quickly verify compliance. The system is scalable and can handle multiple image inputs, ensuring efficient monitoring. By automating PPE identification, it reduces manual effort, minimizes errors, and improves workplace safety management. The integration of lightweight and efficient YOLO architectures ensures optimized detection without compromising accuracy. This project contributes to safety monitoring and compliance verification through intelligent image analysis and deep learning-based object detection.

Keywords: PPE detection, YOLOv26, YOLOv12, deep learning, object detection, workplace safety, Flask, Python, image classification, automated monitoring.