EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Forest Fire Recognition Method Based on Modified Deep CNN Model

Shaoxiong Zheng, Xiangjun Zou, Peng Gao, Qin Zhang, Fei Hu, Yufei Zhou, Zepeng Wu, Weixing Wang, Shihong Chen

Forests · 05.01.2024 · 15 (1) · 111

DOI: 10.3390/f15010111 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Forests, online erschienen am 05.01.2024. Verfasst von Shaoxiong Zheng und 8 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Basic and Applied Basic Research Foundation, Characteristic Innovation Projects of Department of Education of Guangdong Province, Guangdong Forestry Science and Technology Innovation Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Controlling and extinguishing spreading forest fires is a challenging task that often leads to irreversible losses. Moreover, large-scale forest fires generate smoke and dust, causing environmental pollution and posing potential threats to human life. In this study, we introduce a modified deep convolutional neural network model (MDCNN) designed for the recognition and localization of fire in video imagery, employing a deep learning-based recognition approach. We apply transfer learning to refine the model and adapt it for the specific task of fire image recognition. To combat the issue of imprecise detection of flame characteristics, which are prone to misidentification, we integrate a deep CNN with an original feature fusion algorithm. We compile a diverse set of fire and non-fire scenarios to construct a training dataset of flame images, which is then employed to calibrate the model for enhanced flame detection accuracy. The proposed MDCNN model demonstrates a low false alarm rate of 0.563%, a false positive rate of 12.7%, a false negative rate of 5.3%, and a recall rate of 95.4%, and achieves an overall accuracy of 95.8%. The experimental results demonstrate that this method significantly improves the accuracy of flame recognition. The achieved recognition results indicate the model’s strong generalization ability.

Förderung

  • Guangdong Basic and Applied Basic Research Foundation
  • Characteristic Innovation Projects of Department of Education of Guangdong Province
  • Guangdong Forestry Science and Technology Innovation Project
  • Guangdong Provincial Forestry Association Science and Technology Plan Project
  • Guangdong Eco-Engineering Polytechnic textbook construction Project
  • Guangdong Eco-Engineering Polytechnic Double Leader Teacher Party Branch Studio Project

Zitieren

APA

Zheng, S., Zou, X., Gao, P., Zhang, Q., Hu, F., Zhou, Y., Wu, Z., Wang, W., & Chen, S. (2024). A Forest Fire Recognition Method Based on Modified Deep CNN Model. Forests, 15(1), 111. https://doi.org/10.3390/f15010111

Vancouver

Zheng S, Zou X, Gao P, Zhang Q, Hu F, Zhou Y, et al. A Forest Fire Recognition Method Based on Modified Deep CNN Model. Forests. 2024;15(1):111. doi:10.3390/f15010111

BibTeX
@article{Zheng2024,
  author = {Zheng, Shaoxiong and Zou, Xiangjun and Gao, Peng and Zhang, Qin and Hu, Fei and Zhou, Yufei and Wu, Zepeng and Wang, Weixing and Chen, Shihong},
  title = {A Forest Fire Recognition Method Based on Modified Deep CNN Model},
  journal = {Forests},
  year = {2024},
  volume = {15},
  number = {1},
  pages = {111},
  doi = {10.3390/f15010111}
}
Kostenlos starten →