banner
Home > Open Journal Systems

Deep learning framework for forest fire detection using optical images

Devendhar Gogula, Pranav Kumar, Rakesh Sharma

Abstract


Reducing environmental and wildlife losses is a burning challenge as the planet’ s temperature is increasing. Natural calamities, such as forest fires, have a significant influence on both the acceleration of global warming and the sustenance of life on Earth. Research into the automatic diagnosis of forest fires is essential to investigate which can reduce the likelihood of catastrophic events. Early fire detection can also assist decision-makers in planning measures of mitigation and strategies for extinguishing the blaze. The issue with the existing fire detection methods is that there are many false alarms due to the lesser accuracy of the system. This study investigates the ability to spot fires in images using transfer learning models like ResNet50, InceptionV3, and EfficientNetV2L for four different algorithms in terms of accuracy, precision, and recall metrics. Experimental results are also evaluated based on training time, testing accuracy, and validation accuracy. The study addressed the deficiencies that are present in the existing infrastructure and developed a method that is both effective and reliable in its ability to detect forest fires in the beginning stages, with the end goal of preventing the annual waste of tones of resources that is caused by fires.


Keywords


forest fire; machine learning; deep learning; fire detection

Full Text:

PDF

References


1. Bot K, Borges JG. A Systematic Review of Applications of Machine Learning Techniques for Wildfire Management Decision Support. Inventions. 2022; 7(1): 15. doi: 10.3390/inventions7010015

2. Sathishkumar VE, Cho J, Subramanian M, et al. Forest fire and smoke detection using deep learning-based learning without forgetting. Fire Ecology. 2023; 19(1). doi: 10.1186/s42408-022-00165-0

3. Vadivu MS, Vijayalakshmi MN. Efficient Fire Pixel Segmentation Using Color Models in Still Images. International Journal of Computer Sciences and Engineering. 2018; 6(9): 23-28. doi: 10.26438/ijcse/v6i9.2328

4. Kizilkaya B, Ever E, Yatbaz HY, et al. An Effective Forest Fire Detection Framework Using Heterogeneous Wireless Multimedia Sensor Networks. ACM Transactions on Multimedia Computing, Communications, and Applications. 2022; 18(2): 1-21. doi: 10.1145/3473037

5. Zhao L, Zhi L, Zhao C, et al. Fire-YOLO: A Small Target Object Detection Method for Fire Inspection. Sustainability. 2022; 14(9): 4930. doi: 10.3390/su14094930

6. Abid F. A Survey of Machine Learning Algorithms Based Forest Fires Prediction and Detection Systems. Fire Technology. 2020; 57(2): 559-590. doi: 10.1007/s10694-020-01056-z

7. Muhammad A, Khloud K A, Salma A S, et al. Role of Machine Learning Algorithms in Forest Fire Management: A Literature Review. Journal of Robotics and Automation. 2021; 5(1). doi: 10.36959/673/372

8. Bouguettaya A, Zarzour H, Taberkit AM, et al. A review on early wildfire detection from unmanned aerial vehicles using deep learning-based computer vision algorithms. Signal Processing. 2022; 190: 108309. doi: 10.1016/j.sigpro.2021.108309

9. Friggens MM, Loehman RA, Constan CI, et al. Predicting wildfire impacts on the prehistoric archaeological record of the Jemez Mountains, New Mexico, USA. Fire Ecology. 2021; 17(1). doi: 10.1186/s42408-021-00103-6

10. Ha VK, Ren J, Xu X, et al. Deep learning based single image super-resolution: A survey. In: Advances in Brain Inspired Cognitive Systems: 9th International Conference, BICS 2018; 7-8 July 2018; Xi’ an, China. Springer International Publishing. pp. 106-119.

11. Saeed F, Paul A, Karthigaikumar P, et al. Convolutional neural network based early fire detection. Multimedia Tools and Applications. 2019; 79(13-14): 9083-9099. doi: 10.1007/s11042-019-07785-w

12. Majid S, Alenezi F, Masood S, et al. Attention based CNN model for fire detection and localization in real-world images. Expert Systems with Applications. 2022; 189: 116114. doi: 10.1016/j.eswa.2021.116114

13. Fouda MM, Sakib S, Fadlullah ZM, et al. A Lightweight Hierarchical AI Model for UAV-Enabled Edge Computing with Forest-Fire Detection Use-Case. IEEE Network. 2022; 36(6): 38-45. doi: 10.1109/mnet.003.2100325

14. Li P, Zhao W. Image fire detection algorithms based on convolutional neural networks. Case Studies in Thermal Engineering. 2020; 19: 100625. doi: 10.1016/j.csite.2020.100625

15. Janku P, Kominkova Oplatkova Z, Dulik T, et al. Fire Detection in Video Stream by Using Simple Artificial Neural Network. MENDEL. 2018; 24(2). doi: 10.13164/mendel.2018.2.055

16. Shen D, Chen X, Nguyen M, et al. Flame detection using deep learning. In: 2018 4th International Conference on Control, Automation and Robotics (ICCAR). Published online April 2018. doi: 10.1109/iccar.2018.8384711

17. Chen W, Chen S, Guo H, et al. Welding flame detection based on color recognition and progressive probabilistic Hough transform. Concurrency and Computation: Practice and Experience. 2020; 32(19). doi: 10.1002/cpe.5815

18. Mahmoud HAH, Alharbi AH, Alghamdi NS. Time-efficient fire detection convolutional neural network coupled with transfer learning. Intelligent Automation and Soft Computing. 2022; 31(3): 1393–1403. doi: 10.32604/iasc.2022.020629

19. Tan M, Le Q. Efficientnetv2: Smaller models and faster training. In International conference on machine learning. PMLR. 2021. pp. 10096-10106.

20. Cheng X. Research on Application of the Feature Transfer Method Based on Fast R-CNN in Smoke Image Recognition. Advances in Multimedia. 2021; 2021: 1-7. doi: 10.1155/2021/6147860.

21. Sousa MJ, Moutinho A, Almeida M. Wildfire detection using transfer learning on augmented datasets. Expert Systems with Applications. 2020; 142: 112975. doi: 10.1016/j.eswa.2019.112975

22. Guede-Fernández F, Martins L, de Almeida RV, et al. A Deep Learning Based Object Identification System for Forest Fire Detection. Fire. 2021; 4(4): 75. doi: 10.3390/fire4040075

23. Luo Y, Zhao L, Liu P, et al. Fire smoke detection algorithm based on motion characteristic and convolutional neural networks. Multimedia Tools and Applications. 2017; 77(12): 15075-15092. doi: 10.1007/s11042-017-5090-2.

24. Sharma J, Granmo OC, Goodwin M, Fidje JT. Deep convolutional neural networks for fire detection in images. In: Proceedings of Engineering Applications of Neural Networks: 18th International Conference, EANN 2017; 25–27 August 2017; Athens, Greece. Springer International Publishing. pp. 183-193.

25. Muhammad K, Ahmad J, Baik SW. Early fire detection using convolutional neural networks during surveillance for effective disaster management. Neurocomputing. 2018; 288: 30-42. doi: 10.1016/j.neucom.2017.04.083

26. Qin YY, Cao JT, Ji XF. Fire Detection Method Based on Depthwise Separable Convolution and YOLOv3. International Journal of Automation and Computing. 2021; 18(2): 300-310. doi: 10.1007/s11633-020-1269-5

27. Jeon M, Choi HS, Lee J, et al. Multi-Scale Prediction for Fire Detection Using Convolutional Neural Network. Fire Technology. 2021; 57(5): 2533-2551. doi: 10.1007/s10694-021-01132-y

28. IEEE SCOReD IEEE Student Conference on Research and Development Putrajaya, Malaysia, IEEE Malaysia Section, IEEE XPlore Conference Proceedings Online, Institute of Electrical and Electronics Engineers, & Universiti Tenaga Nasional. (2010).

29. Shamsoshoara A, Afghah F, Razi A, et al. Aerial imagery pile burn detection using deep learning: The FLAME dataset. Computer Networks. 2021; 193: 108001. doi: 10.1016/j.comnet.2021.108001

30. Srividhya S, Sindhu S, Sornalakshmi K, et al. Fire Detection System using Deep Learning Techniques. In: 2022 4th International Conference on Inventive Research in Computing Applications (ICIRCA). Published online September 21, 2022. doi: 10.1109/icirca54612.2022.9985499

31. Seydi ST, Saeidi V, Kalantar B, et al. Fire-Net: A Deep Learning Framework for Active Forest Fire Detection. Journal of Sensors. 2022; 2022: 1-14. doi: 10.1155/2022/8044390

32. Bari A, Saini T, Kumar A. Fire Detection Using Deep Transfer Learning on Surveillance Videos. 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV). Published online February 4, 2021. doi: 10.1109/icicv50876.2021.9388485

33. He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Published online June 2016. doi: 10.1109/cvpr.2016.90

34. Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Published online June 2016. doi: 10.1109/cvpr.2016.308

35. Tan M, & L, Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR. 2019. pp. 6105-6114.

36. Mascarenhas S, Agarwal M. A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for Image Classification. In: Proceedings of 2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON). doi: 10.1109/centcon52345.2021.9687944




DOI: https://doi.org/10.32629/jai.v7i5.1522

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 Devendhar Gogula, Pranav Kumar, Rakesh Sharma

License URL: https://creativecommons.org/licenses/by-nc/4.0/