İnsansız Hava Araçları ile Orman Yangınlarının Tespitinde Görüntü İşleme ve Yapay Zekâ Tabanlı Otomatik Bir Model

Abstract

Nefes almak için gereksinim duyduğumuz oksijenin büyük bir kısmı, hayatta kalabilmemiz için hayati öneme sahip olan ormanlar tarafından üretilir. Bu yüzden ormanları korumak, içinde yaşadığımız yüzyılın en önemli konu başlıklarından bir tanesidir. Dünyanın farklı coğrafyalarında (ABD, Avustralya vb.) her yıl meydana gelen orman yangınları ciddi ekonomik kayba neden olmakta ve ekosistemi olumsuz olarak etkilemektedir. Ateşin çeşitli renk, şekil ve doku özelliklerine sahip olması orman yangınlarının uzaktan algılanmasını zorlaştırmaktadır. Yapılan bu çalışmada orman yangınlarının tespitinde insansız hava araçları vasıtasıyla tamamen otomatik bir sistem önerilmiştir. Ormanlık arazinin tespitinde uydu görüntüleri üzerine görüntü bölütleme yöntemi kullanılmış, insansız hava aracının tespit edilen bölgeyi en kısa zamanda ve en az görüntü ile kontrol edebilmesi için de küme kaplama yöntemi kullanılmıştır. Daha sonra elde edilen imgeler üretilen yapay zekâya dayalı ateş algılama modeline göre değerlendirilip başlangıç ve ileri aşamadaki yangınlar tespit edilmiş ve konumları elde edilmiştir. Sonuç olarak, yapılan çalışmada yaklaşık %97,51 değerinde doğrulukla yangın tespit eden bir erken uyarı modeli önerilmektedir.

Keywords

• Yangın Algılama
• Görüntü İşleme
• Küme Kaplama
• Yapay Zekâ

An Automatic Model Based on Image Processing and Artificial Intelligence via Unmanned Aerial Vehicles in Detection of Forest Fires

Abstract

Most of the oxygen we need to breathe is produced by forests, which are vital to our survival. Therefore, protecting forests is one of the most critical issues of the century. Forest fires that occur every year in different geographies of the World (USA, Australia etc.) cause severe economic loss and negatively affect the ecosystem. The fact that fire has various colors, shapes, and textures makes it challenging to detect forest fires from a distance. In this study, a fully automatic system is proposed by means of unmanned aerial vehicles in the detection of forest fires. The image segmentation method on satellite images was used in the detection of the forested land, and the cluster overlay method was used in order for the unmanned aerial vehicle to control the detected area in the shortest time and with the least amount of images.Then, the images obtained were evaluated according to the fire detection model based on artificial intelligence, and the initial and advanced stage fires were determined, and their locations were obtained. As a result, an early warning model that detects fire with an accuracy of approximately 97.51% is proposed in the study.

Keywords

• Fire Detection
• Image Processing
• Set Covering
• Artificial Intelligence

References

1. [1] A. Dhall, A. Dhasade, A. Nalwade, M. Raj, and V. Kulkarni, “A survey on systematic approaches in managing forest fires,” Appl. Geogr., vol. 121, no. 102266, p. 102266, 2020.
2. [2] A. Bouguettaya, H. Zarzour, A. M. Taberkit, and A. Kechida, “A review on early wildfire detection from unmanned aerial vehicles using deep learning-based computer vision algorithms,” Signal Processing, vol. 190, no. 108309, p. 108309, 2022.
3. [3] M. A. Enoh, U. C. Okeke, and N. Y. Narinua, “Identification and modelling of forest fire severity and risk zones in the Cross – Niger transition forest with remotely sensed satellite data,” Egypt. J. Remote Sens. Space Sci., vol. 24, no. 3, pp. 879–887, 2021.
4. [4] F. Sivrikaya and Ö. Küçük, “Modeling forest fire risk based on GIS-based analytical hierarchy process and statistical analysis in Mediterranean region,” Ecol. Inform., vol. 68, no. 101537, p. 101537, 2022.
5. [5] M. Naderpour, H. M. Rizeei, N. Khakzad, and B. Pradhan, “Forest fire induced Natech risk assessment: A survey of geospatial technologies,” Reliab. Eng. Syst. Saf., vol. 191, no. 106558, p. 106558, 2019.
6. [6] S. Chaturvedi, P. Khanna, and A. Ojha, “A survey on vision-based outdoor smoke detection techniques for environmental safety,” ISPRS J. Photogramm. Remote Sens., vol. 185, pp. 158–187, 2022.
7. [7] M.D. Flannıgan, B.D. Amıro, K.A. Logan, B.J. Stocks and B.M. Wotton, Forest Fires and Climate Change In The 21st Century, Mitigation and Adaptation Strategies for Global Change, vol.11, pp.847–859, 2005.
8. [8] B. Christensen, “Technological advances in rural fire management: use of organizational knowledge and simple economic analysis”, Lincoln University, 2014.

9. [9] J. San-Miguel-Ayanz, “Forest fires in Europe, middle east and north Africa 2017,” 2017.
10. [10] M. Mutlu, S. C. Popescu, and K. Zhao, “Sensitivity analysis of fire behavior modeling with LIDAR-derived surface fuel maps,” For. Ecol. Manage., vol. 256, no. 3, pp. 289–294, 2008.
11. [11] T. J. Duff and K. G. Tolhurst, “Operational wildfire suppression modelling: a review evaluating development, state of the art and future directions,” Int. J. Wildland Fire, vol. 24, no. 6, p. 735, 2015.
12. [12] M. Francos and X. Úbeda, “Prescribed fire management,” Curr. opin. environ. sci. health, vol. 21, no. 100250, p. 100250, 2021.
13. [13] M. Avcı ve M. Korkmaz, “Türkiye’de orman yangını sorunu: Güncel bazı konular üzerine değerlendirmeler”, Turkish Journal of Forestry, vol. 22, no.3, s. 229-240, 2021.
14. [14] E. Bilgili, İ. Baysal, B. Dinç Durmaz, B. Sağlam, Ö. Küçük, “2008 yılında çıkan büyük orman yangınlarının değerlendirilmesi”, III. Ulusal Karadeniz Ormancılık Kongresi, 20-22 Mayıs, Artvin, s. 1270-1279, 2010.
15. [15] E. Bilgili, B. Dinç Durmaz, İ. Baysal, B. Sağlam, Ö. Küçük, “Doğu Karadeniz ormanlarında orman yangınları” III. Ulusal Karadeniz Ormancılık Kongresi, 20-22 Mayıs, Artvin, s. 1280-1290, 2010.
16. [16] E. Bilgili, Ö. Küçük, B. Sağlam and K.A. Coşkuner, “Mega Forest Fıres: Causes, Organızatıon And Management”, Forest Fires”, Ankara, Türkiye Bilimler Akademisi, s. 1-23, 2021.
17. [17] E. Bilgili, Ö. Küçük, B. Sağlam, İ. Baysal, B.D. Durmaz ve K.A. Coşkuner, “Türkiye Orman Ekosistemlerinde Yangınların Ekolojik Rolü”, Ekoloji ve Ekonomi Ekseninde Türkiye’de Orman ve Ormancılık, Ankara: Sonçağ Akademi, s. 75-115, 2021.
18. [18] K.A. Coşkuner ve E. Bilgili, “Orman yangın yönetiminde etkili bir karar destek sisteminin kavramsal çerçevesi”, Doğal Afetler ve Çevre Dergisi, s.6, no.2, s. 288-303, 2020.
19. [19] G. Narasimha Rao, P. Jagadeeswara Rao, R. Duvvuru, S. Bendalam, and R. Gemechu, “Fire detection in kambalakonda reserved forest, visakhapatnam, Andhra pradesh, India: An internet of things approach,” Mater. Today, vol. 5, no. 1, pp. 1162–1168, 2018.
20. [20] A. Sharma et al., “IoT and deep learning-inspired multi-model framework for monitoring Active Fire Locations in Agricultural Activities,” Comput. Electr. Eng., vol. 93, no. 107216, pp. 107216, 2021.
21. [21] P. Kanakaraja, P. Syam Sundar, N. Vaishnavi, S. Gopal Krishna Reddy, and G. Sai Manikanta, “IoT enabled advanced forest fire detecting and monitoring on Ubidots platform,” Mater. Today, vol. 46, pp. 3907–3914, 2021.
22. [22] F. T. AL-Dhief, N. Sabri, S. Fouad, N. M. A. Latiff, and M. A. A. Albader, “A review of forest fire surveillance technologies: Mobile ad-hoc network routing protocols perspective,” J. King Saud Univ. - Comput. Inf. Sci., vol. 31, no. 2, pp. 135–146, 2019.
23. [23] J. R. Martínez-de Dios, L. Merino, F. Caballero, A. Ollero, and D. X. Viegas, “Experimental results of automatic fire detection and monitoring with UAVs,” For. Ecol. Manage., vol. 234, p. S232, 2006.
24. [24] J. R. M. Dios, L. Merino, and A. Ollero, “Fire detection using autonomous aerial vehicles with infrared and visual cameras,” IFAC proc. vol., vol. 38, no. 1, pp. 660–665, 2005.
25. [25] A. Martins et al., “Forest fire detection with a small fixed wing autonomous aerial vehicle,” IFAC proc. vol., vol. 40, no. 15, pp. 168–173, 2007.
26. [26] O. Ozkan, “Optimization of the distance-constrained multi-based multi-UAV routing problem with simulated annealing and local search-based matheuristic to detect forest fires: The case of Turkey,” Appl. Soft Comput., vol. 113, no. 108015, p. 108015, 2021.
27. [27] S. Sudhakar, V. Vijayakumar, C. Sathiya 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,” Comput. Commun., vol. 149, pp. 1–16, 2020.
28. [28] M. Mohajane et al., “Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area,” Ecol. Indic., vol. 129, no. 107869, p. 107869, 2021.
29. [29] K. R. Singh, K. P. Neethu, K. Madhurekaa, A. Harita, and P. Mohan, “Parallel SVM model for forest fire prediction,” Soft Computing Letters, vol. 3, no. 100014, p. 100014, 2021
30. [30] C. Filizzola et al., “RST-FIRES, an exportable algorithm for early-fire detection and monitoring: description, implementation, and field validation in the case of the MSG-SEVIRI sensor,” Remote Sens. Environ., vol. 186, pp. 196–216, 2016.
31. [31] P. Bernabeu, L. Vergara, I. Bosh, and J. Igual, “A prediction/detection scheme for automatic forest fire surveillance,” Digit. Signal Process., vol. 14, no. 5, pp. 481–507, 2004.
32. [32] M. J. Sousa, A. Moutinho, and M. Almeida, “Wildfire detection using transfer learning on augmented datasets,” Expert Syst. Appl., vol. 142, no. 112975, p. 112975, 2020.
33. [33] X. Yang et al., “Pixel-level automatic annotation for forest fire image,” Eng. Appl. Artif. Intell., vol. 104, no. 104353, p. 104353, 2021.
34. [34] A. Sharma, P. K. Singh, and Y. Kumar, “An integrated fire detection system using IoT and image processing technique for smart cities,” Sustain. Cities Soc., vol. 61, no. 102332, p. 102332, 2020.
35. [35] Z. Liu, K. Zhang, C. Wang, and S. Huang, “Research on the identification method for the forest fire based on deep learning,” Optik (Stuttg.), vol. 223, no. 165491, p. 165491, 2020.
36. [36] Y. Hu et al., “Fast forest fire smoke detection using MVMNet,” Knowl. Based Syst., vol. 241, no. 108219, p. 108219, 2022.
37. [37] L. Wang, J. J. Qu, and X. Hao, “Forest fire detection using the normalized multi-band drought index (NMDI) with satellite measurements,” Agric. For. Meteorol., vol. 148, no. 11, pp. 1767–1776, 2008.
38. [38] B. Aksoy, K. Korucu, Ö. Çalişkan, Ş. Osmanbey, and H. D. Hali̇s, “İnsansız Hava Aracı ile Görüntü İşleme ve Yapay Zekâ Teknikleri Kullanılarak Yangın Tespiti: Örnek Bir Uygulama,” Düzce Üniv. bilim ve teknol. derg., pp. 112–122, 2021.
39. [39] F. Bulut , İ. Kılıç ve İ. F. İnce, "Beyin Tümörü Tespitinde Görüntü Bölütleme Yöntemlerine Ait Başarımların Karşılaştırılması ve Analizi", Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi, c. 20, sayı. 58, s. 173-186, Oca. 2018.
40. [40] M. S. Daskin, Network and discrete location: Models, algorithms, and applications. Hoboken, NJ, USA: John Wiley & Sons, Inc., 1995.
41. [41] M.A. Khan, W. Ectors, T. Bellemans, D. Janssens, G. Wets, “UAV-Based Traffic Analysis: A Universal Guiding Framework Based on Literature Survey, Transportation Research Procedia”, vol. 22, pp. 541-550, 2017.
42. [42] “Fire Dataset,” Kaggle. [Online]. Available: https://www.kaggle.com/datasets/phylake1337/fire-dataset. [Accessed: 04-Spring-2022].
43. [43] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv [cs.CV], 2014.
44. [44] A. Krizhevsky, I. Sutskever and G. Hinton, "ImageNet classification with deep convolutional neural networks." In NIPS’2012, 23, 24, 27, 100, 200, 371, 456, 460, 2012.
45. [45] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
46. [46] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
47. [47] U. Konur , "Sınıflandırma Başarımını Ölçme ve Seyreklik İşleme Üzerine", EMO Bilimsel Dergi, c. 10, sayı. 2, s. 43-56, Ara. 2020.
48. [48] F. Cui, “Deployment and integration of smart sensors with IoT devices detecting fire disasters in huge forest environment,” Comput. Commun., vol. 150, pp. 818–827, 2020.
49. [49] Z. Jiao et al., “A YOLOv3-based learning strategy for real-time UAV-based forest fire detection,” in 2020 Chinese Control And Decision Conference (CCDC), 2020.