Authors : Q. M. Murtazayev; B. B. Choriyev

Volume/Issue : Volume 11 - 2026, Issue 9 - September

Google Scholar : https://tinyurl.com/36su498y

DOI : https://doi.org/10.38124/ijisrt/26sep274

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : This article addresses the use of artificial intelligence-based software tools for the early detection of fires that may occur in buildings and structures and for the rapid notification of the parties concerned. Within the scope of the study, the real-time analysis of images and video streams obtained from video surveillance systems is examined, together with the possibilities of automatically detecting the earliest signs of fire, in particular smoke and flame. To improve the accuracy and speed of the fire-detection process, the advantages of software approaches based on computer vision and deep learning technologies are analyzed. In addition, the automation of the processes for promptly delivering information on a detected fire to responsible persons and for issuing timely notifications is described. The results of the study are aimed at improving artificial intelligence-based software tools that serve to ensure fire safety in buildings and structures, to detect fires at an early stage, and to reduce their adverse consequences.

Keywords : Fire, Buildings and Structures, Early Detection, Rapid Notification, Artificial Intelligence, Software Tools, Computer Vision, Deep Learning, Video Surveillance, Smoke Detection, Flame Detection, Real-Time Mode, Fire Safety.

References :

1. Murtazayev, Q.M., & Choriyev, B.B. (2023). Bino va inshootlarda sodir bo‘lgan yong‘inlarni zamonaviy xabarlash tizimlari asosida aniqlashning usul va vositalarini takomillashtirish [Improvement of methods and means for detecting fires in buildings and structures based on modern notification systems]. Yong‘in-portlash xavfsizligi jurnali [Journal of Fire and Explosion Safety], December 2023.
2. Murtazayev, Q.M., & Choriyev, B.B. (2024). Improvement of methods and means of rapid notification of possible fires in buildings and constructions. Science and Innovation International Scientific Journal, 3(12), 37–43.
3. Choriyev, B.B. (2026). Bino va inshootlarda sodir bo‘lishi mumkin bo‘lgan yong‘inlarni tezkor xabarlash dasturiy ta’minoti joriy etish va samaradorligini baholash [Implementation and effectiveness evaluation of software for the rapid notification of possible fires in buildings and structures]. Proceedings of the International Scientific-Practical Conference “30 Years of Emergency Situations Authorities: Path of Development, Reforms and Prospects,” 2026, pp. 409–413.
4. Wu, H., Wu, D., & Zhao, J. An intelligent fire detection approach through cameras based on computer vision methods.
5. Kai-Kuang, M. (2008). Computer vision based fire detection in color images. 2008 IEEE Conference on Soft Computing in Industrial Applications, 258–263.
6. Chen, T.H., Wu, P.H., & Chiou, Y.C. (2004). An early fire-detection method based on image processing. ICIP Proceedings — International Conference on Image Processing, 1707–1710.
7. Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008). Speeded-up robust features (SURF). Computer Vision and Image Understanding, 110(3), 346–359. https://doi.org/10.1016/j.cviu.2007.09.014
8. Luo, P., Tian, Y., Wang, X., & Tang, X. (2014). Switchable deep network for pedestrian detection. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (pp. 899–905). Columbus, OH, USA.
9. Vadim, K., Maxime, O., Minsu, C., & Laptev, I. (2016). ContextLocNet: Context-aware deep network models for weakly supervised localization. In European Conference on Computer Vision (Vol. 1, No. 2, pp. 350–365).
10. Wang, Z., & Liu, J. (2017). A review of object detection based on convolutional neural network. In 36th Chinese Control Conference (pp. 11104–11109). Dalian, China.
11. Çelik, T., Özkaramanlı, H., & Demirel, H. (2007). Fire and smoke detection without sensors: Image processing based approach. In Proceedings of the 15th European Signal Processing Conference (pp. 1794–1798). Poznan, Poland.
12. Krizhevsky, A., Sutskever, I., & Hinton, G.E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84–90.
13. Foggia, P., Saggese, A., & Vento, M. (2015). Real-time fire detection for video-surveillance applications using a combination of experts based on colour, shape, and motion. IEEE Transactions on Circuits and Systems for Video Technology, 25(9), 1545–1556.