ABSTRACT
Wildfires can cause significant damage to forests and endanger wildlife. Detecting these forest fires at the initial stages helps the authorities in preventing them from spreading further. In this paper, we first propose a novel technique, termed CIELAB-color technique, which detects fire based on the color of the fire in CIELAB color space. We train state-of-art CNNs to detect fire. Since deep learning (CNNs) and image processing have complementary strengths, we combine their strengths to propose an ensemble architecture. It uses two CNNs and the CIELAB-color technique and then performs majority voting to decide the final fire/no-fire prediction output. We finally propose a chain-of-classifiers technique which first tests an image using the CIELAB-color technique. If an image is flagged as no-fire, then it further checks the image using a CNN. This technique has lower model size than ensemble technique. On FLAME dataset, the ensemble technique provides 93.32% accuracy, outperforming both previous works ( accuracy) and individually using either CNNs or CIELAB-color technique. The source code can be obtained from https://github.com/CandleLabAI/FireDetection.
- Turgay Celik. 2010. Fast and Efficient Method for Fire Detection Using Image Processing. ETRI Journal 32 (12 2010). https://doi.org/10.4218/etrij.10.0109.0695Google Scholar
- Y. Chen, Y. Zhang, J. Xin, G. Wang, L. Mu, Y. Yi, H. Liu, and D. Liu. 19–21 June 2019. UAV Image-based Forest Fire Detection Approach Using Convolutional Neural Network. 14th IEEE Conference on Industrial Electronics and Applications (ICIEA), Xi’an, China, 2118–2123.Google Scholar
- Alexandra Delazio, Ali Israr, and Roberta Klatzky. 2017. Cross-modal correspondence between vibrations and colors. 219–224.Google Scholar
- Frederic Flament, Virginie Hourblin, and Stephanie Nouveau. 2014. Skin Color Types and Indian Skin Characteristics. 47–61.Google Scholar
- Rafik Ghali, Moulay Akhloufi, and Wided Mseddi. 2022. Deep Learning and Transformer Approaches for UAV-Based Wildfire Detection and Segmentation. Sensors 22 (03 2022).Google Scholar
- Zhihao Guan, Xinyu Miao, Yunjie Mu, Quan Sun, Qiaolin Ye, and Demin Gao. 2022. Forest Fire Segmentation from Aerial Imagery Data Using an Improved Instance Segmentation Model. Remote Sensing 14 (07 2022), 3159.Google Scholar
- W. Lee, S. Kim, Y.T. Lee, H.W. Lee, and M. Choi. 12–14 June 2017. Deep neural networks for wild fire detection with unmanned aerial vehicle. IEEE International Conference on Consumer Electronics (ICCE), Taipei, Taiwan, 252–253.Google Scholar
- Subhrajit Nag 2021. ARCN: A Real-time Attention-based Network for Crowd Counting from Drone Images. In IEEE 18th India Council International Conference (INDICON).Google ScholarCross Ref
- Poonam Rajput, Subhrajit Nag, and Sparsh Mittal. 2020. Detecting Usage of Mobile Phones using Deep Learning Technique. In 6th EAI International Conference on Smart Objects and Technologies for Social Good (GOODTECHS). 96–101.Google ScholarDigital Library
- A. Shamsoshoara, F. Afghah, A. Razi, L. Zheng, P.Z. Fulé, and E. Blasch. 2020. The FLAME Dataset: Aerial Imagery Pile Burn Detection Using Drones (UAVs). IEEE DataPort: New York, NY, USA(2020).Google Scholar
- A. Shamsoshoara, F. Afghah, A. Razi, L. Zheng, P.Z. Fulé, and E. Blasch. 2021. Aerial Imagery Pile burn detection using Deep Learning: the FLAME dataset. Comput. Netw. (2021).Google Scholar
- K. Srinivas and M. Dua. 26–28 February 2020. Fog Computing and Deep CNN Based Efficient Approach to Early Forest Fire Detection with Unmanned Aerial Vehicles. International Conference on Inventive Computation Technologies, Coimbatore, India, 646–652.Google Scholar
- Srishti Srivastava, Sarthak Narayan, and Sparsh Mittal. 2021. A Survey of Deep Learning Techniques for Vehicle Detection from UAV Images. Journal of Systems Architecture 117 (2021), 102152.Google ScholarDigital Library
- S. Treneska and B.R. Stojkoska. 6–7 May 2021. Wildfire detection from UAV collected images using transfer learning. 18th International Conference on Informatics and Information Technologies, Skopje, North Macedonia.Google Scholar
- Y. Zhao, J. Ma, X. Li, and J. Zhang. 2018. Saliency Detection and Deep Learning-Based Wildfire Identification in UAV Imagery. Sensors (2018).Google Scholar
Recommendations
A uniform illumination image enhancement via linear transformation in CIELAB color space
AbstractDigital devices such as digital cameras and smartphones are important tools in capturing color images. However, images captured under a low-light condition have low contrast, low brightness, and they lose their color information. In this paper, we ...
An efficient deep neural network with color-weighted loss for fire detection
AbstractFire is one of the most harmful hazards that affect daily life. Compared with sensor-based methods, vision-based methods have more advantages in fire detection. Existing approaches fail to achieve a good trade-off among fire locations, false ...
Combining Neural Networks and a Color Classifier for Fire Detection
Intelligent SystemsAbstractDeep learning methods have solved several problems in the computer vision area, mainly for image classification. The use of these methods for fire detection can bring great improvements to security systems and prevent many losses. Effective fire ...
Comments