Integrating Yolo for Real-Time Fire Detection in Smart Surveillance Systems

Abstract

Fire and smoke detection systems are essential for safeguarding lives and property by preventing catastrophic damage. However, traditional detection methods, such as heat sensors and smoke detectors, often exhibit limitations like delayed response times and a high rate of false positives, especially in large-scale or dynamic environments. The increasing prevalence of forest fires, driven by climate change, results in severe economic losses and environmental destruction. While wildfires can sometimes promote vegetation growth and support wildlife, their destructive impact remains a major threat to communities and ecosystems.To address the need for more effective fire management, this study introduces a real-time fire and smoke detection system using the You Only Look Once (YOLO) algorithm, a cutting-edge object detection framework. YOLO’s ability to swiftly detect and classify objects from images and video streams makes it particularly well-suited for identifying fire and smoke across diverse settings, including indoor, outdoor, and low-visibility conditions. By training the model on a comprehensive dataset of annotated fire and smoke images, the proposed system achieves exceptional detection accuracy and low latency. This ensures reliable real-world deployment, facilitating early detection and minimizing the risk of fire-related damage.