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

Authors

  • P. Rajalakshmi Student, Department of CSE, Chendhuran College of Engineering & Technology, Pudukkottai, Tamil Nadu, India Author
  • Mrs. P. Rohini Assistant Professor & Head, Department of CSE, Chendhuran College of Engineering & Technology, Pudukkottai, Tamil Nadu, India Author

DOI:

https://doi.org/10.32628/CSEIT25113347

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.

Downloads

Download data is not yet available.

References

Jung, Daekyo, et al. "Conceptual framework of an intelligent decision support system for smart city disaster management." Applied Sciences 10.2 (2020): 666.

Minsoo, Park, et al. "Wildfire-Detection Method Using DenseNet and CycleGAN Data Augmentation-Based Remote Camera Imagery [J]." Remote Sensing 12.22 (2020): 3715-3715

Park, Minsoo, et al. "Multilabel image classification with deep transfer learning for decision support on wildfire response." Remote Sensing 13.19 (2021): 3985.

Zhang, Jianmei, et al. "ATT squeeze U-Net: A lightweight network for forest fire detection and recognition." IEEE Access 9 (2021): 10858-10870.

Xu, Renjie, et al. "A forest fire detection system based on ensemble learning." Forests 12.2 (2021): 217.

Guede-Fernández, Federico, et al. "A deep learning-based object identification system for forest fire detection." Fire 4.4 (2021): 75.

Arab, Ali, et al. "Three lines of defense for wildfire risk management in electric power grids: A review." IEEE Access 9 (2021): 61577-61593.

Martins, Leonardo, et al. "Real-Time Integration of Segmentation Techniques for Reduction of False Positive Rates in Fire Plume Detection Systems during Forest Fires." Remote Sensing 14.11 (2022): 2701.

Kang, Yoojin, et al. "Developing a new hourly forest fire risk index based on catboost in South Korea." Applied Sciences 10.22 (2020): 8213.

Tran, Dai Quoc, et al. "Damage-map estimation using UAV images and deep learning algorithms for disaster management system." Remote Sensing 12.24 (2020): 4169.

Downloads

Published

31-05-2025

Issue

Section

Research Articles