Fire Detection System using YOLOv5 and IoT Integration for Real-Time Alerts in Safety Applications

Abstract

The rising threat of heat-related and fire incidents underscores the urgent need for advanced thermal and fire detection systems to ensure timely and accurate responses. This report presents a smart fire detection project utilizing the YOLOv5 deep learning model. The project aims to design an early fire detection system with real-time capabilities. The proposed system implements a convolutional neural network (CNN) and the YOLOv5 real-time object identification system, enhancing fire detection through anchor box optimization. In the incident of a fire, the system sends an alert to the user’s Telegram app bot via the Internet of Things (IoT), assisting in taking necessary precautions. The project demonstrates notable efficiency in fire detection and alerting capabilities, with system evaluation metrics showing an F1 score of 95%, mAP@50 of 97%, accuracy 96.3%, and a recall rate of 89%. These results underscore the system's reliability and precision. The project contributes significantly to Sustainable Development Goals (SDG), goal 9 for industry, innovation, and infrastructure, and 11 for sustainable cities and communities highlighting its potential to enhance fire safety measures in various settings.