Video-Based Fire Detection
Copyright (c) 2024 Tóth Attila, Tóth Levente
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Abstract
Fire incidents pose a significant threat to human life and property security, making early detection crucial for mitigating potential damage. Traditional fire alarm systems predominantly depend on smoke detectors or thermal sensors, which may be insufficient in certain scenarios (such as intricate, compartmentalized settings) to promptly detect the emerging fire. However, technological advancements in recent years have opened new possibilities in this field. The integration of artificial intelligence (AI) and video analytics has proven to be a promising solution for improving fire detection capabilities. The application of AI-based video analytics allows systems to detect fires much faster and more accurately, even in their early stages. By using smart cameras and computer vision techniques, fire alarm systems can identify various visual signs of fire, such as smoke, flames, and temperature changes. Unlike traditional fire alarm systems, AI-based solutions can continuously learn and adapt to new information, enhancing detection accuracy. Additionally, the data collected by smart cameras can be analyzed in real-time, enabling quicker response and intervention. These systems can also distinguish between real threats and harmless phenomena, reducing the number of false alarms. This article examines in detail the development and application of AI-based video analytics in fire detection. It also presents the current challenges and future development directions in this field to better understand the potential of AI and video analytics in fire detection.
Keywords:
How to Cite
References
BERMAN, Dana – TALI, Treibitz – SHAI, Avidan (2016): Non-Local Image Dehazing. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE. Online: https://doi.org/10.1109/CVPR.2016.185
CHAROSKAR, Rohit et al. (2023): Fire Detection and Localization in Video Surveillance Application. International Journal of Advanced Research in Science, Communication and Technology, 3(1), 457–460. Online: https://doi.org/10.48175/IJARSCT-9066
CHEONG, Kwang-Ho – KO, Byoung-Chul – NAM, Jae-Yeal (2008): Automatic Fire Detection System Using CCD Camera and Bayesian Network. Electronic Imaging, SPIE6813. Online: https://doi.org/10.1117/12.764822
CHETOUI, Mohamed – AKHLOUFI, Moulay A. (2024): Fire and Smoke Detection Using Fine-Tuned YOLOv8 and YOLOv7 Deep Models. Fire, 7(4), 135. Online: https://doi.org/10.3390/fire7040135
CIMER, Zsolt (2021): Application of Chemical Monitoring and Public Alarm Systems to Reduce Public Vulnerability to Major Accidents Involving Dangerous Substances. Symmetry, 13(8), 1528. Online: https://doi.org/10.3390/sym13081528
ÉRCES Gergő – VASS Gyula (2018): Veszélyes ipari üzemek tűzvédelme ipari üzemek fenntartható tűzbiztonságának fejlesztési lehetőségei a komplex tűzvédelem tekintetében. Műszaki Katonai Közlöny, 28(4), 2–22. Online: https://bit.ly/3ZuWnaP
HE, Lijun et al. (2021): Efficient Attention Based Deep Fusion CNN for Smoke Detection in Fog Environment. Neurocomputing, 434, 224–238. Online: https://doi.org/10.1016/j.neucom.2021.01.024
KÁTAI-URBÁN, Maxim (2023): Identification Methodology for Chemical Warehouses Dealing with Flammable Substances Capable of Causing Firewater Pollution. Fire, 6(9), 345. Online: https://doi.org/10.3390/fire6090345
MUHAMMAD, Khan et al. (2018): Convolutional Neural Networks Based Fire Detection in Surveillance Videos. IEEE Access, 6, 18174–18183. Online: https://doi.org/10.1109/ACCESS.2018.2812835
NAGULAN, S. et al. (2022): An Efficient Real-Time Fire Detection Method Using Computer Vision and Neural Network-Based Video Analysis. In Proceedings of Third Doctoral Symposium on Computational Intelligence, 627–637. Online: https://doi.org/10.1007/978-981-19-3148-2_55
PLUMB, O. Augustus – RICHARDS, F. (1996): Development of an Economical Video Based Fire Detection and Location System. National Institute of Standards and Technology.
RIYADI, D. Slamet – AISYAH, Siti (2018): Vision Based Flame Detection System For Surveillance Camera. 2018 International Conference on Applied Engineering (ICAE), Batam. Online: https://doi.org/10.1109/INCAE.2018.8579405
SANJANA, S. et al. (2022): Deep Learning Models for Fire Detection Using Surveillance Cameras in Public Places. 13th International Conference on Computing Communication and Networking Technologies. Kharagpur: IEEE. 1–7. Online: https://doi.org/10.1109/ICCCNT54827.2022.9984601
TÓTH Attila (2018): Az élőerő munkáját segítő technikai megoldások. Hadmérnök, 13(2), 29–36. Online: http://hadmernok.hu/182_03_toth.pdf
TÓTH, Levente (2017): Resolution Limit of Small Image Sensors Size. Acta Technica Corviniensis – Bulletin of Engineering, 2, 39–44. Online: https://acta.fih.upt.ro/pdf/2017-2/ACTA-2017-2-05.pdf
TÓTH Levente (2018): Kisformátumú képbontók határfelbontás korlátai. Hadmérnök, 13(3), 38–49. Online: http://hadmernok.hu/183_04_toth.pdf
XU, Zhengguang – XU, Jialin (2007): Automatic Fire Smoke Detection Based on Image Visual Features. 2007 International Conference on Computational Intelligence and Security Workshops (CISW 2007), Harbin. 316–319. Online: https://doi.org/10.1109/CISW.2007.4425500