Fire Detection and Verification Using Convolutional Neural Networks, Masked Autoencoder and Transfer Learning

  • Zainab Abed Almoussawi College of Islamic Science, Ahl Al Bayt University, Kerbala, Iraq
  • Raed Khalid
  • Zahraa Salam Obaid
  • Zuhair I. Al Mashhadani
  • Kadhum Al-Majdi
  • Refad E. Alsaddon
  • Hassan Mohammed Abed
Keywords: Fire detection, convolutional neural networks, masked auto encoder, vision transformers, transfer learning

Abstract

Wildfire detection is a time-critical application since it can be challenging to identify the source of ignition in a short amount of time, which frequently causes the intensity of fire incidents to increase. The development of precise early-warning applications has sparked significant interest in expert systems research due to this issue, and recent advances in deep learning for challenging visual interpretation tasks have created new study avenues. In recent years the power of deep learning-based models sparked the researcher’s interests from a variety of fields. Specially, convolutional neural networks (CNN) have become the most suited approach for computer vision tasks. As a result, in this paper we propose a CNN-based pipeline for classifying and verifying fire-related images. Our approach consists of two models, first of which classifies the input data and then the second model verifies the decision made by the first one by learning more robust representations obtained from a large masked auto encoder-based model. The verification step boosts the performance of the classifier with respect to false positives and false negatives. Based on extensive experiments, our approach proves to improve previous state-of-the-art algorithms by 3 to 4% in terms of accuracy.

References

[1] Kim, Byoungjun, and Joonwhoan Lee. "A video-based fire detection using deep learning models." Applied Sciences 9, no. 14, p. 2862, 2019.
[2] Avazov, Kuldoshbay, Mukhriddin Mukhiddinov, Fazliddin Makhmudov, and Young Im Cho. "Fire Detection Method in Smart City Environments Using a Deep-Learning-Based Approach." Electronics 11, no. 1, p. 73, 2021.
[3] Xu, Renjie, Haifeng Lin, Kangjie Lu, Lin Cao, and Yunfei Liu. "A forest fire detection system based on ensemble learning." Forests 12, no. 2, p. 217, 2021.
[4] Kang, Li-Wei, I-Shan Wang, Ke-Lin Chou, Shih-Yu Chen, and Chuan-Yu Chang. "Image-based real-time fire detection using deep learning with data augmentation for vision-based surveillance applications." In 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), no. 2, pp. 1-4. IEEE, 2019.
[5] Barmpoutis, Panagiotis, Kosmas Dimitropoulos, Kyriaki Kaza, and Nikos Grammalidis. "Fire detection from images using faster R-CNN and multidimensional texture analysis." In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), no.14, pp. 8301-8305. IEEE, 2019.
[6] Xue, Zhenyang, Haifeng Lin, and Fang Wang. "A Small Target Forest Fire Detection Model Based on YOLOv5 Improvement." Forests 13, no. 8, p. 1332, 2022.
[7] Molajou, Amir, Vahid Nourani, Abbas Afshar, Mina Khosravi, and Adam Brysiewicz. "Optimal design and feature selection by genetic algorithm for emotional artificial neural network (EANN) in rainfall-runoff modeling." Water Resources Management 35, no. 8, 2369-2384, 2021.
[8] Sharghi, Elnaz, Vahid Nourani, Hessam Najafi, and Amir Molajou. "Emotional ANN (EANN) and wavelet-ANN (WANN) approaches for Markovian and seasonal based modeling of rainfall-runoff process." Water resources management 32, no. 10, pp. 3441-3456, 2018.
[9] Nourani, Vahid, Zahra Razzaghzadeh, Aida Hosseini Baghanam, and Amir Molajou. "ANN-based statistical downscaling of climatic parameters using decision tree predictor screening method." Theoretical and Applied Climatology 137, no. 3, pp. 1729-1746, 2019.
[10] Monteiro, Vitor, Julio S. Martins, João Carlos Aparício Fernandes, and Joao L. Afonso. "Review of a disruptive vision of future power grids: a new path based on hybrid AC/DC grids and solid-state transformers." Sustainability 13, no. 16, pp. 9423, 2021.
[10] H. R. Ebrahimi, H. Usefi, H. Emami, and G. R. Amiri, “Synthesis, characterization, and sensing performance investigation of copper cadmium ferrite nanoparticles,” IEEE Trans. Magn., vol. 54, no. 10, Oct. 2018, Art. no. 4000905.
[11] Monteiro, Vitor, Julio S. Martins, João Carlos Aparício Fernandes, and Joao L. Afonso. "Review of a disruptive vision of future power grids: a new path based on hybrid AC/DC grids and solid-state transformers." Sustainability 13, no. 16, p. 9423, 2021.
[12] Xiao, Tete, Mannat Singh, Eric Mintun, Trevor Darrell, Piotr Dollár, and Ross Girshick. "Early convolutions help transformers see better." Advances in Neural Information Processing Systems 34, pp. 30392-30400, 2021.
[13] Zhang, Jinnian, Houwen Peng, Kan Wu, Mengchen Liu, Bin Xiao, Jianlong Fu, and Lu Yuan. "MiniViT: Compressing Vision Transformers with Weight Multiplexing." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, no. 5, pp. 12145-12154. 2022.
[14] Bazi, Yakoub, Laila Bashmal, Mohamad M. Al Rahhal, Reham Al Dayil, and Naif Al Ajlan. "Vision transformers for remote sensing image classification." Remote Sensing 13, no. 3, p. 516, 2021.
[15] Zhuang, Fuzhen, Zhiyuan Qi, Keyu Duan, Dongbo Xi, Yongchun Zhu, Hengshu Zhu, Hui Xiong, and Qing He. "A comprehensive survey on transfer learning." Proceedings of the IEEE 109, no. 1, pp. 43-76, 2020.
[16] Raffel, Colin, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. "Exploring the limits of transfer learning with a unified text-to-text transformer." J. Mach. Learn. Res. 21, no. 140, pp. 1-67, 2020.
[17] He, Kaiming, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, and Ross Girshick. "Masked autoencoders are scalable vision learners." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, no. 8, pp. 16000-16009. 2022.
[18] Giri, Ritwik, Srikanth V. Tenneti, Karim Helwani, Fangzhou Cheng, Umut Isik, and Arvindh Krishnaswamy. "Unsupervised anomalous sound detection using self-supervised classification and group masked autoencoder for density estimation." Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2020 Challenge), Tech. Rep, no.7, p. 23, 202.
[19] Weihan, Wang. "MAGAN: A masked autoencoder generative adversarial network for processing missing IoT sequence data." Pattern Recognition Letters, no. 138, pp. 211-216, 2020.
[20] Khajenezhad, Ahmad, Hatef Madani, and Hamid Beigy. "Masked autoencoder for distribution estimation on small structured data sets." IEEE Transactions on Neural Networks and Learning Systems 32, no. 11, pp. 4997-5007, 2020.
[21] Shao, Zhenzhou, Ying Qu, Guangli Ren, Guohui Wang, Yong Guan, Zhiping Shi, and Jindong Tan. "Batch Normalization Masked Sparse Autoencoder for Robotic Grasping Detection." In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), no. 6, pp. 9614-9619. IEEE, 2020.
[22] Matsui, Ayaka, Shota Asahi, Satoshi Tamura, Satoru Hayamizu, Ryosuke Isashi, Akira Furukawa, and Takayoshi Naitou. "Anomaly detection in mechanical vibration using combination of signal processing and autoencoder." Journal of Signal Processing 24, no. 4, pp. 203-206, 2020.
[23] Brand, Fabian, Kristian Fischer, and André Kaup. "Rate-Distortion Optimized Learning-Based Image Compression using an Adaptive Hierachical Autoencoder with Conditional Hyperprior." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, no.22, pp. 1885-1889. 2021.
[24] Dou, Zeyang, Kun Gao, Xiaodian Zhang, Hong Wang, and Lu Han. "Band selection of hyperspectral images using attention-based autoencoders." IEEE Geoscience and Remote Sensing Letters 18, no. 1, pp. 147-151, 2020.
[25] de Rooij, Mark, and Wouter Weeda. "Cross-validation: A method every psychologist should know." Advances in Methods and Practices in Psychological Science 3, no. 2, pp. 248-263, 2020.
[26] Wong, Tzu-Tsung, and Po-Yang Yeh. "Reliable accuracy estimates from k-fold cross validation." IEEE Transactions on Knowledge and Data Engineering 32, no. 8, pp. 1586-1594, 2019.
[27] Fong, Edwin, and Chris C. Holmes. "On the marginal likelihood and cross-validation." Biometrika 107, no. 2, pp. 489-496, 2020.
[28] Lopez-del Rio, Angela, Alfons Nonell-Canals, David Vidal, and Alexandre Perera-Lluna. "Evaluation of cross-validation strategies in sequence-based binding prediction using deep learning." Journal of chemical information and modeling 59, no. 4, pp. 1645-1657, 2019.
[29] Tian, Chunwei, Lunke Fei, Wenxian Zheng, Yong Xu, Wangmeng Zuo, and Chia-Wen Lin. "Deep learning on image denoising: An overview." Neural Networks, no. 131, pp. 251-275, 2020.
[30] Bartlett, Peter L., Andrea Montanari, and Alexander Rakhlin. "Deep learning: a statistical viewpoint." Acta numerica, no. 30, pp. 87-201, 2021.
Published
2022-11-07
How to Cite
Almoussawi, Z. A., Khalid, R., Obaid, Z. S., Al Mashhadani, Z. I., Al-Majdi, K., Alsaddon, R. E., & Abed, H. M. (2022). Fire Detection and Verification Using Convolutional Neural Networks, Masked Autoencoder and Transfer Learning. Majlesi Journal of Electrical Engineering. Retrieved from http://mjee.iaumajlesi.ac.ir/index/index.php/ee/article/view/4927
Section
Articles

Most read articles by the same author(s)