Fire Detection Using Unmanned Aerial Vehicle Imaging Processing and Artificial Intelligence Techniques: A Sample Application

Year 2021, Volume: 9 Issue: 6 - ICAIAME 2021, 112 - 122, 31.12.2021

Bekir Aksoy , Kaan Korucu , Önder Çalışkan Şaban Osmanbey Helin Diyar Halis

https://doi.org/10.29130/dubited.1016195

Cited By: 2

Abstract

The increase in forest and city fires in recent years is an important problem for the whole world. Fires, which cause great ecological and economic losses, also cause serious damage to forest dynamics by disrupting the carbon cycle. In this direction, it is important to protect forests and nature, which are important ecosystems in terms of the necessity of life. In the fight against forest and city fires, early detection of fire prevents great losses. With the development of technology, unmanned aerial vehicles (UAV), artificial intelligence and image processing techniques are used in order to detect fires early. The study focused on the early detection of the fire and an unmanned aerial vehicle was designed to detect the fire early. In the study, fire detection is made in the images by using image processing and artificial intelligence techniques, and then the location where the fire is detected is determined. As a result, the performance of the architecture used in the study was evaluated according to the complexity matrix, and the values of 96% accuracy, 98% sensitivity, 89% specificity and 96% precision were found. Thanks to the work carried out, early detection of the fire will be ensured and rapid intervention will be carried out.

Keywords

Unmanned aerial vehicle, Fire detection, Image processing, Artificial intelligence

İnsansız Hava Aracı ile Görüntü İşleme ve Yapay Zekâ Teknikleri Kullanılarak Yangın Tespiti: Örnek Bir Uygulama

Abstract

Son yıllarda orman ve şehir yangınlarının artması tüm dünya için önemli bir sorun oluşturmaktadır. Ekolojik ve ekonomik açıdan büyük kayıplara sebep olan yangınlar, karbon döngüsünü bozarak orman dinamiklerine de ciddi zarar vermektedir. Bu doğrultuda yaşamın gerekliliği açısından önemli ekosistemlerden olan ormanların ve doğanın korunması önem arz etmektedir. Orman ve şehir yangınları ile mücadelede yangının erken tespiti büyük kayıpların önüne geçmektedir. Teknolojinin gelişimi ile birlikte yangınların erken tespit edilebilmesi amacıyla insansız hava araçları (İHA), yapay zekâ ve görüntü işleme tekniklerinden yararlanılmaktadır. Çalışmada, yangının erken tespiti üzerinde duruldu ve yangının erken tespit edilebilmesi için insansız hava aracı tasarlandı. Çalışmada, görüntü işleme ve yapay zekâ tekniklerinden yararlanılarak görüntülerde ateş tespiti yapılmakta ve akabinde yangın tespit edilen konum belirlenmektedir. Çalışmada sonuç olarak kullanılan mimarinin karmaşıklık matrisine göre performansı değerlendirilerek, %96 doğruluk, %98 duyarlılık, %89 özgüllük ve %96 kesinlik değerleri bulunmuştur. Gerçekleştirilen çalışma sayesinde yangının erken tespiti sağlanacak ve hızlı müdahale gerçekleştirilecektir.

Keywords

İnsansız hava aracı, Yangın tespiti, Görüntü işleme, Yapay Zekâ

Thanks

Çalışmada kullanılan “FIRE-Dataset” açık kaynak verilerini internet sitesinde (Kaggle) kullanıma açan herkese teşekkürlerimizi sunarız.

References

• [1] J.E. Watson, T. Evans, O. Venter, B. Williams, A. Tulloch, C. Stewart, I. Thompson, J.C. Ray, K. Murray, A. Salazar, C. McAlpine, P. Potapov, J. Walston, J.G. Robinson, M. Painter, D. Wilkie, C. Filardi, W.F. Laurance, R.A. Houghton, S. Maxwell, H. Grantham, C. Samper, S. Wang, L. Laestadius, R.K. Runting, G.A. Silva-Chávez, J. Ervinand D. Lindenmayer, “The exceptional value of intact forest ecosystems,” Nature Ecology&Evolution, vol. 2, no. 4, pp. 599-610, 2018.
• [2] V. Sevinc, O. Kucuk and M. Goltas,“A Bayesian network model forpredictionandanalysis of possible forest fire causes,”Forest Ecologyand Management, vol. 457, 2020.
• [3] G. Zhang, M. Wang and K. Liu,“Forest fire susceptibilitymodelingusing a convolutionalneural network forYunnanprovince of China,” International Journal of Disaster Risk Science, vol. 10, no. 3, pp. 386-403, 2019.
• [4] D. Tezza and M. Andujar, “The state-of-the-art of human–drone interaction: A survey,” IEEE Access, vol. 7, pp. 167438-167454, 2019.
• [5] A. Hosny, C. Parmar, J. Quackenbush, L. H. Schwartz and H. J.Aerts, “Artificial intelligence in radiology,” Nature Reviews Cancer, vol. 18, no. 8, pp. 500-510, 2018.
• [6] S. R. Balaji and S. Karthikeyan, “A survey on moving object tracking using image processing,”IEEE 11th International Conference on Intelligent Systems and Control, 2017, pp. 469-474.
• [7] X. Deng, Y.Ma and M. Dong, “A new adaptive filtering method for removing salt and peppernoise based on multilayered PCNN,” Pattern Recognition Letters, vol. 79, pp. 8-17, 2016.
• [8] A. Mohan and S. Poobal, “Crack detection using image processing: A critical review and analysis,”Alexandria Engineering Journal, vol. 57, no. 2, pp. 787-798, 2018.
• [9] H. Michalak, and K. Okarma, “Improvement of imagebinarization methods using image preprocessing with localentropy filtering for alpha numerical character recognition purposes,” Entropy,vol. 21, no. 6, 2019.
• [10] O. Özkaraca, Y. Dere, G. Çetin ve M. Peker, “A computeraided system for calculation of Ki-67 proliferationindex,” IEEE, In 2017 International Conference on ComputerScience and Engineering, 2017, pp. 580-585.
• [11] S. D. Khirade and A.B. Patil, “Plant disease detection using image processing,” IEEE, In 2015 International Conference on Computing Communication Control and Automation, 2015, pp. 768-771.
• [12] O. Bingöl, ve Ö. Kuşcu, “Bilgisayar tabanlı araç plaka tanıma sistemi,” Bilişim Teknolojileri Dergisi, c. 1, s. 3, 2008.
• [13] C. Yuan, Z. Liu and Y. Zhang, “UAV-based forest fire detection and tracking using image processing techniques,” IEEE, In 2015 International Conference on Unmanned Aircraft Systems, 2015, pp. 639-643.
• [14] C. Yuan, K. A. Ghamry, Z. Liu and Y. Zhang,“Unmanned aerial vehicle based forest fire monitoring and detection using image processing technique,”In 2016 IEEE Chinese Guidance, Navigation and Control Conference, 2016, pp. 1870-1875.
• [15] S. Sudhakar, V. Vijayakumar, C.S. Kumar, V. Priya, L. Ravi and V. Subramaniyaswamy, “Unmanned Aerial Vehicle (UAV) based Forest Fire Detection and monitoring for reducing false alarms in forest-fires,”Computer Communications, vol. 149, pp. 1-16, 2020.
• [16] W. Lee, S. Kim, Y.T. Lee, H.W. Lee and M. Choi, “Deep neural networks for wild fire detection with unmanned aerial vehicle,”In 2017 IEEE İnternational Conference on Consumer Electronics, 2017, pp. 252-253.
• [17] A. Said, (2021, Oct. 11), Fire-Dataset, [Online]. Available: https://www.kaggle.com/.
• [18] X. Xu and Y. Deng, “UAV power component—DC brushless motor de-sign with merging adjacentdisturbances and integrated-dispatching pigeon-inspired optimization,”IEEE Transactions on Magnetics, vol. 54, no. 8, pp. 1-7, 2018.
• [19] F. Santoso, M.A Garratt and S.G Anavatti, “State-of-the-art intelli-gent flight control systems in unmanned aerial vehicles,” IEEE Transactions on Automation Science and Engineering, vol. 15, no. 2, pp. 613-627, 2017.
• [20] X. Xue, “Optimization of Electronic Speed Controller (ESC) Power Quality,” Ph.D. dissertation, Dept. Electrical Engineering, San Diego State University, USA, 2019.
• [21] A. Kumar and S.S. Sodhi, “Comparative analysis of gaussian filter, median filter and denoise autoenocoder,”IEEE, 7th International Conference on Computing for Sustainable Global Development, 2020, pp. 45-51.
• [22] Y. Li, M. Abdel-Monem, R. Gopalakrishnan, M. Berecibar, E. Nanini-Maury, N. Omar and J. Van Mierlo, “A quick on-line state of health estimation method for Liion battery with incremental capacity curves processed by Gaussian filter,” Journal of Power Sources, vol. 373, pp. 40-53, 2018.
• [23] W. Dong, S. Xiao and Y. Li, “Hyperspectral pansharpening based on guided filter and Gaussian filter,” Journal of Visual Communication and Image Representation,vol. 53, pp. 171-179, 2018.
• [24] T. Y. Goh, S. N. Basah, H. Yazid, M. J. A. Safar and F. S. A Saad, “Performance analysis of image thresholding: Otsu technique,” Measurement, vol. 114, pp. 298-307, 2018.
• [25] M. Abdel-Basset, V. Chang and R. Mohamed, “A novel equilibrium optimization algorithm for multi-thresholding image segmentation problems,”Neural Computing and Applications, vol. 33, no. 17, pp. 10685-10718, 2021.
• [26] A. K. M. Khairuzzaman and S. Chaudhury, “Multilevel thresholding using grey wolf optimizer for image segmentation,” Expert Systems with Applications,vol. 86, pp. 64-76, 2017.
• [27] F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally and K. Keutzer, “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size,” 2016, arXiv:1602.07360.
• [28] F. Ucar and D. Korkmaz,“COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images,” Medical Hypotheses, vol. 140, 2020.
• [29] G. I. Sayed, M. M. Soliman and A. E. Hassanien, “A novel melanoma prediction model for imbalanced data using optimized SqueezeNet by bald eagle search optimization,” Computers in Biology and Medicine, vol. 136, 2021, Art. no. 104712.
• [30] A. Luque, A. Carrasco, A. Martín andA. Heras, “The impact of class imbalance in classification performance metrics based on the binary confusion matrix,” Pattern Recognition, vol. 91, pp. 216-231, 2019.