Active Fire Detection in Forests with 5 Deep Learning Techniques

  • Marcelo Kuchar Matte UFMS
  • José Marcato Junior UFMS
  • Newton Loebens UCDB
  • Hemerson Pistori UCDB

Resumo


Identifying active fires in natural and difficult-to-access environments is a real and current problem, especially in recent years. One of the simplest ways to monitor regions of difficult access is the use of satellite images in their various patterns, such as multi-spectral and hyper-spectral images. In this way, we used 5 CNNs (Faster R-CNN, ATSS, RetinaNet, VfNet, and SABL) to detect active fires in satellite images of the Pantanal region in May 2020. In preliminary results, it was possible to reach values greater than 50% of mAP50 in the detections performed. Studies are still ongoing in the search for higher precisions.

Referências

P. Jain, S. C. Coogan, S. G. Subramanian, M. Crowley, S. Taylor, and M. D. Flannigan, “A review of machine learning applications in wildfire science and management,” Environmental Reviews, vol. 28, no. 4, pp. 478–505, 2020.

R. Ba, C. Chen, J. Yuan, W. Song, and S. Lo, “Smokenet: Satellite smoke scene detection using convolutional neural network with spatial and channel-wise attention,” Remote Sensing, vol. 11, no. 14, 2019. [Online]. Available: https://www.mdpi.com/2072-4292/11/14/1702

G. H. de Almeida Pereira, A. M. Fusioka, B. T. Nassu, and R. Minetto, “Active fire detection in landsat-8 imagery: a large-scale dataset and a deep-learning study,” 2021.

S. Jana and S. K. Shome, “Hybrid ensemble based machine learning for smart building fire detection using multi modal sensor data,” Fire Technology, vol. 59, no. 2, pp. 473–496, 2023.

S. Jia, S. Jiang, Z. Lin, N. Li, M. Xu, and S. Yu, “A survey: Deep learning for hyperspectral image classification with few labeled samples,” Neurocomputing, vol. 448, pp. 179–204, 2021.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Advances in neural information processing systems, vol. 25, pp. 1097–1105, 2012.

R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 580–587.

R. Girshick, “Fast r-cnn,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1440–1448.

S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: towards real-time object detection with region proposal networks,” IEEE transactions on pattern analysis and machine intelligence, vol. 39, no. 6, pp. 1137–1149, 2016.

T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980–2988.

S. Zhang, C. Chi, Y. Yao, Z. Lei, and S. Z. Li, “Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9759–9768.

J. Wang, W. Zhang, Y. Cao, K. Chen, J. Pang, T. Gong, J. Shi, C. C. Loy, and D. Lin, “Side-aware boundary localization for more precise object detection,” in European Conference on Computer Vision. Springer, 2020, pp. 403–419.

H. Zhang, Y. Wang, F. Dayoub, and N. Sunderhauf, “Varifocalnet: An iou-aware dense object detector,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 8514–8523.

D. Hamilton, E. Levandovsky, and N. Hamilton, “Mapping burn extent of large wildland fires from satellite imagery using machine learning trained from localized hyperspatial imagery,” Remote Sensing, vol. 12, no. 24, p. 4097, 2020.

X. Hu, Y. Ban, and A. Nascetti, “Uni-temporal multispectral imagery for burned area mapping with deep learning,” Remote Sensing, vol. 13, no. 8, p. 1509, 2021.

V. Khryashchev and R. Larionov, “Wildfire segmentation on satellite images using deep learning,” in 2020 Moscow Workshop on Electronic and Networking Technologies (MWENT), 2020, pp. 1–5.

P. Pednekar, A. Srivastava, and A. Jadhav, “Fire detection using transfer learning and pre-trained model,” in 2023 3rd International Conference on Intelligent Technologies (CONIT). IEEE, 2023, pp. 1–4.

M. M. Pinto, R. M. Trigo, I. F. Trigo, and C. C. DaCamara, “A practical method for high-resolution burned area monitoring using sentinel-2 and viirs,” Remote Sensing, vol. 13, no. 9, p. 1608, 2021.

R. Singh, S. Sharma, S. Sharma, and S. Kaushik, “Real-time fire detection system based on cnn using tensorflow and opencv,” Journal of Data Acquisition and Processing, vol. 38, no. 2, p. 723, 2023.

L. Higa, J. Marcato Junior, T. Rodrigues, P. Zamboni, R. Silva, L. Almeida, V. Liesenberg, F. Roque, R. Libonati, W. N. Gonçalves et al., “Active fire mapping on brazilian pantanal based on deep learning and cbers 04a imagery,” Remote Sensing, vol. 14, no. 3, p. 688, 2022.

K. Chen, J. Wang, and et al., “MMDetection: Open mmlab detection toolbox and benchmark,” arXiv preprint arXiv:1906.07155, 2019.
Publicado
13/11/2023
MATTE, Marcelo Kuchar; MARCATO JUNIOR, José; LOEBENS, Newton; PISTORI, Hemerson. Active Fire Detection in Forests with 5 Deep Learning Techniques. In: WORKSHOP DE VISÃO COMPUTACIONAL (WVC), 18. , 2023, São Bernardo do Campo/SP. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 1-5. DOI: https://doi.org/10.5753/wvc.2023.27523.

Artigos mais lidos do(s) mesmo(s) autor(es)

Obs.: Esse plugin requer que pelo menos um plugin de estatísticas/relatórios esteja habilitado. Se o seu plugins de estatísticas oferece mais que uma métrica, então, por favor, também selecione uma métrica principal na página de configurações administrativas do site e/ou da revista.