Affiliation:
1. College of Computer Science, Chengdu University, Chengdu 610106, China
2. Sichuan Province Engineering Technology Research Center of Healthy Human Settlement, Chengdu 610225, China
3. Sichuan University Engineering Design & Research Institute Co., Ltd., Chengdu 610225, China
Abstract
Cameras, especially those carried by drones, are the main tools used to detect wildfires in forests because cameras have much longer detection ranges than smoke sensors. Currently, deep learning is main method used for fire detection in images, and Transformer is the best algorithm. Swin Transformer restricts the computation to a fixed-size window, which reduces the amount of computation to a certain extent, but to allow pixel communication between windows, it adopts a shift window approach. Therefore, Swin Transformer requires multiple shifts to extend the receptive field to the entire image. This somewhat limits the network’s ability to capture global features at different scales. To solve this problem, instead of using the shift window method to allow pixel communication between windows, we downsample the feature map to the window size after capturing global features through a single Transformer, and we upsample the feature map to the original size and add it to the previous feature map. This way, there is no need for multiple layers of stacked window Transformers; global features are captured after each window Transformer operation. We conducted experiments on the Corsican fire dataset captured by ground cameras and on the Flame dataset captured by drone cameras. The results show that our algorithm performs the best. On the Corsican fire dataset, the mIoU, F1 score, and OA reached 79.4%, 76.6%, and 96.9%, respectively. On the Flame dataset, the mIoU, F1 score, and OA reached 84.4%, 81.6%, and 99.9%, respectively.
Funder
Sichuan Province Engineering Technology Research Center of Healthy Human Settlement
Reference54 articles.
1. Peñuelas, J., and Sardans, J. (2021). Global Change and Forest Disturbances in the Mediterranean Basin: Breakthroughs, Knowledge Gaps, and Recommendations. Forests, 12.
2. Land use change towards forests and wooded land correlates with large and frequent wildfires in Italy;Davide;Ann. Silvic. Res.,2021
3. Forest Fires and Losses Caused by Fires–An Economic Approach;Sadowska;WSEAS Trans. Environ. Dev.,2021
4. Zhang, J., Li, W., Yin, Z., Liu, S., and Guo, X. (2009, January 25–27). Forest fire detection system based on wireless sensor network. Proceedings of the 2009 4th IEEE Conference on Industrial Electronics and Applications, Xi’an, China.
5. Yu, L., Wang, N., and Meng, X. (2005, January 26). Real-time forest fire detection with wireless sensor networks. Proceedings of the 2005 International Conference on Wireless Communications, Networking and Mobile Computing, Wuhan, China.