Forest Fire Detection Using Multi-Modal Learning on RGB/IR Dataset
Forest Fire Detection Using Multi-Modal Learning on RGB/IR Dataset |
||
 |
 |
|
| © 2024 by IJETT Journal | ||
| Volume-72 Issue-11 |
||
| Year of Publication : 2024 | ||
| Author : Tilottama Goswami, Apuru Rohan, Varkala Sujith Atesh, Kovvur Ram Mohan Rao |
||
| DOI : 10.14445/22315381/IJETT-V72I11P119 | ||
How to Cite?
Tilottama Goswami, Apuru Rohan, Varkala Sujith Atesh, Kovvur Ram Mohan Rao, "Forest Fire Detection Using Multi-Modal Learning on RGB/IR Dataset," International Journal of Engineering Trends and Technology, vol. 72, no. 11, pp. 175-183, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I11P119
Abstract
A forest fire is an uncontrolled fire that spreads rapidly and occurs in forests or other wildlands. Early detection of these kinds of fires is crucial to protecting the environment, vegetation, and wildlife. Several methods have been proposed to detect early forest fires and respond rapidly to emergency teams. The method proposed in the paper improves detection accuracy and identifies the fire's accurate position. This work uses multimodal learning, using two kinds of data from the same scene, IR and RGB, to detect forest fires. It proposes a deep learning-based methodology for detecting fire and smoke pixels at an accuracy much higher than the usual single-channel RGB or IR images. It classifies them into three classes using a deep learning methodology: - Fire without smoke - Fire with smoke - Smoke without fire. The models proposed are trained on the FLAME2 Dataset. The images are classified with a good accuracy of 99\%. In addition, the work uses image processing methods that detect the position of fire in the image and provide some real-time analysis of the feed.
Keywords
Deep learning, Ensemble learning, K-fold validation, Segmentation, CNN.
References
[1] Richard Skinner et al., “A Literature Review on The Impact of Wildfires on Emergency Departments: Enhancing Disaster Preparedness,” Prehospital and Disaster Medicine, vol. 37, no. 5, pp. 657-664, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Yongsong Huang et al., “Infrared Image Super-Resolution: Systematic Review, and Future Trends,” arXiv, pp. 1-18, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Ammar Mohammed, and Rania Kora, “A Comprehensive Review on Ensemble Deep Learning: Opportunities and Challenges,” Journal of King Saud University-Computer and Information Sciences, vol. 35, no. 2, pp. 757-774, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Nida M. Zaitoun, and Musbah J. Aqel, “Survey on Image Segmentation Techniques,” Procedia Computer Science, vol. 65, pp. 797-806, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[5] S. Prince Mary et al., “A Survey on Image Segmentation Using Deep Learning,” Journal of Physics: Conference Series, vol. 1712. no. 1, pp. 1-10, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] D. Hema, and S. Kannan, “Interactive Color Image Segmentation Using HSV Color Space,” Science and Technology Journal, vol. 7, no. 1, pp. 37-41, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Herbert Bousack et al., “Towards Improved Airborne Fire Detection Systems Using Beetle Inspired Infrared Detection and Fire Searching Strategies,” Micromachines, vol. 6, no. 6, pp. 718-746, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[8] P. Raghavendra Reddy, and P. Kalyanasundaram, “Novel Detection of Forest Fire Using Temperature and Carbon Dioxide Sensors with Improved Accuracy in Comparison Between Two Different Zones,” Proceedings 2022 3rd International Conference on Intelligent Engineering and Management (ICIEM), London, United Kingdom, pp. 524-527, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Alexander A. Khamukhin, and Silvano Bertoldo, “Spectral Analysis of Forest Fire Noise for Early Detection Using Wireless Sensor Networks,” Proceedings 2016 International Siberian Conference on Control and Communications (SIBCON), Moscow, Russia, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Abdelmalek Bouguettaya et al., “A Review on Early Wildfire Detection from Unmanned Aerial Vehicles Using Deep Learning-Based Computer Vision Algorithms,” Signal Processing, vol. 190, pp. 1-14, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Leonardo Millan-Garcia et al., “An Early Fire Detection Algorithm Using IP Cameras,” Sensors, vol. 12, no. 5, pp. 5670-5686, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Bryce Hopkins et al., “FLAME 2: Fire Detection and Modeling: Aerial Multi-Spectral Image Dataset,” IEEE DataPort, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Norsuzila Ya'acob et al., “Image Processing based Forest Fire Detection Using Infrared Camera,” Proceedings 2nd International Conference on Space Weather and Satellite Application (ICeSSAT), Selangor, Malaysia, vol. 1768, no. 1, pp. 1-13, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Seyd Teymoor Seydi et al., “Fire‐Net: A Deep Learning Framework for Active Forest Fire Detection,” Journal of Sensors, vol. 2022, no. 1, pp. 1-14, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Arpit Jadon, Akshay Varshney, and Mohammad Samar Ansari, “Low-Complexity High-Performance Deep Learning Model for Real-Time Low-Cost Embedded Fire Detection Systems,” Procedia Computer Science, vol. 171, pp. 418-426, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[16] S. NASA, “Fire Information for Resource Management System,” FIRMS, 2020. [Google Scholar] [Publisher Link] [17] Vladimir Sergeevich Bochkov, and Liliya Yurievna Kataeva, “wUUNET: Advanced Fully Convolutional Neural Network for Multiclass Fire Segmentation,” Symmetry, vol. 13, no. 1, pp. 1-18, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Pu Li, and Wangda Zhao, “Image Fire Detection Algorithms Based on Convolutional Neural Networks,” Case Studies in Thermal Engineering, vol. 19, pp. 1-11, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] MinJi Park, and Byoung Chul Ko, “Two-Step Real-Time Night-Time Fire Detection in an Urban Environment Using Static ELASTIC-YOLOv3 and Temporal Fire-Tube,” Sensors, vol. 20, no. 8, pp. 1-17, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Wei Liu et al., “SSD: Single Shot Multibox Detector,” Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, vol. 9905, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Xiwen Chen et al., “Wildland Fire Detection and Monitoring Using a Drone-Collected RGB/IR Image Dataset,” IEEE Access, vol. 10, pp. 121301-121317, 2022.
[CrossRef] [Google Scholar] [Publisher Link]