LIFE SAFETY IN THE AGRICULTURAL SECTOR: IMPLEMENTATION OF A MATHEMATICAL MODEL OF MACHINE VISION FOR DETECTING FIRES IN THE FIELDS
DOI:
https://doi.org/10.35546/kntu2078-4481.2025.2.1.11Keywords:
life safety, fire, fire, smoke, field, machine vision, mathematical modelAbstract
The article highlights the issue of timely detection of fires in agricultural fields, the spread of which causes significant economic losses and poses a threat to the safety of both workers and the surrounding population. An improved fire detection algorithm is proposed, based on a developed mathematical model for a computer vision system that can be installed on unmanned aerial vehicles (UAVs). An analysis of the use of computer vision tools in agriculture for fire detection has shown that, at present, powerful neural networks have been developed for recognizing forest fires, but they typically require stationary computing resources. The aim of the study is to develop a computationally lightweight and efficient mathematical model for a computer vision system capable of detecting fires in agricultural fields, serving as a tool to enhance the safety of workers. A computer vision algorithm is proposed, and its performance is demonstrated using images of field fires. During experimental tests, the system successfully identified smoke and fire locations, highlighting them in blue and red, respectively, and notifying the UAV operator. Due to the system’s ability to promptly detect fires in real time, emergency services can respond quickly, thereby reducing the spread of the fire. Timely fire detection not only minimizes the loss of agricultural land and reduces economic damage, but also significantly lowers the risks to human health and life for those who may be near the ignition source. Moreover, early detection contributes to the reduction of toxic combustion emissions into the atmosphere, positively impacting environmental safety. Thus, the integration of computer vision into fire monitoring systems is a crucial step toward enhancing life safety in the agricultural sector.
References
Гуліда Е. М., Ренкас А. А. Вплив пожеж на екологічну безпеку навколишнього середовища. Науковий вісник НГУ : Екологічна безпека, охорона праці. 2014, № 5, С. 91–100.
Toreyin B. U., Dedeoglu Y., Gueduekbay U. Computer vision based method for real-time fire and flame detection. Pattern Recognition Letters. 2006, 27(1), рр. 49–58.
Kinaneva D., Hristov G., Raychev J., Zahariev P. Early forest fire detection using drones and artificial intelligence. 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics. MIPRO. 2019, Proceedings, art. no. 8756696, pp. 1060–1065. DOI: 10.23919/MIPRO.2019.8756696
Borges P., Izquierdo E. A Probabilistic Approach for Vision-Based Fire Detection in Videos. IEEE Trans. Circuits Syst. Video Technol. 2010, 20, рр. 721–731.
Ryu J., Kwak D. Flame Detection Using Appearance-Based Pre-Processing and Convolutional Neural Network. Appl. Sci. 2021, 11, рр. 5138.
Yuan C., Ghamry K. A., Liu Z., Zhang Y. Unmanned aerial vehicle based forest fire monitoring and detection using image processing technique. In Proceedings of the 2016 IEEE Chinese Guidance, Navigation and Control Conference (CGNCC), Nanjing, China, 12–14 August 2016; pp. 1870–1875.
Jindal P., Gupta H., Pachauri N., Sharma V., Verma O.P. Real-Time Wildfire Detection via Image-Based Deep Learning Algorithm. In Soft Computing: Theories and Applications. Springer: Singapore. 2021, pp. 539–550.
Li P., Zhao W. Image fire detection algorithms based on convolutional neural networks. Case Stud. Therm. Eng. 2020, 19, рр. 100625.
Barmpoutis P., Dimitropoulos K., Kaza K., Grammalidis N. Fire Detection from Images Using Faster R-CNN and Multidimensional Texture Analysis. In Proceedings of the ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 12–17 May 2019, pp. 8301–8305.
Xu R., Lin H., Lu K., Cao L., Liu Y. A Forest Fire Detection System Based on Ensemble Learning. Forests. 2021, 12, рр. 217.
Lu P., Zhao Y., Xu Y. A Two-Stream CNN Model with Adaptive Adjustment of Receptive Field Dedicated to Flame Region Detection. Symmetry. 2021, 13, рр. 397.
Kanivets O. V., Kanivets I. M., Gorda T. M., Burlaka O. A. Development of a machine vision program to determine the completeness of wrapping plants in the soil, CEUR Workshop Proceedings. 2022, Vol. 3077, pp. 27–43. URL: https://ceur-ws.org/Vol-3077/paper04.pdf
F. M. AnimHossain, Youmin M. Zhang, Masuda AkterTonima Forest fire flame and smoke detection from UAV- captured images using fire-specific color features and multi-color space local binary pattern. Journal of Unmanned Vehicle Systems. 2020, 8(4), рр. 285-309. DOI: 10.1139/juvs-2020-0009
Chen X., Hopkins B., Wang H., O’Neill L., Afghah F., Razi A., Fulé P., Coen J., Rowell E., Watts A. Wildland Fire Detection and Monitoring Using a Drone-Collected RGB/IR Image Dataset, IEEE Access. 2022, 10, pp. 121301–121317. DOI: 10.1109/ACCESS.2022.3222805
Nelson K. N., Boehmler J. M., Khlystov A. Y., Moosmüller H., Samburova V., Bhattarai C., Wilcox E. M., Watts A. C. A multipollutant smoke emissions sensing and sampling instrument package for unmanned aircraft systems: Development and testing. Fire. 2019, 2(2), art. no. 32, pp. 1–18. DOI: 10.3390/fire2020032
