EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Image-Based Fire Detection Using Dynamic Threshold Grayscale Segmentation and Residual Network Transfer Learning

Hai Li, Peng Sun

Mathematics · 16.09.2023 · 11 (18) · 3940

DOI: 10.3390/math11183940 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 16.09.2023. Verfasst von Hai Li und 1 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Civil Aviation Education Talent Foundation, Autonomous Project of Sichuan Key Laboratory of Civil Aircraft Fire Science and Safety Engineering, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Research on fire detection based on deep learning has been increasing lately, and current models differ in accuracy and computational complexity. To reduce the loss of semantic information and improve prediction accuracy, this paper combines dynamic threshold grayscale segmentation and residual network transfer learning. An effective training data extension strategy integrates the experimental data of a real fire platform and a forest-image-based fire database, where the experimental data of the real fire platform are shot based on different lighting and backgrounds. It has been proven that this is a good solution that can effectively solve the problem of training robust deep models relying on datasets with large diversity, which can improve the overall performance of the training model. Then, we introduce a network architecture based on dynamic threshold grayscale segmentation and residual net transfer learning, which reaches residual net level accuracy on image-based fire detection tasks with less computation. We train the model with a self-built image dataset, test it on a general fire image dataset, and evaluate it on a self-built fire video dataset. In numerous experiments, our method produced a training and testing accuracy of 98.26% and 99.90%, respectively, with corresponding losses of 0.036 and 0.04. The evaluation accuracy was 90% under the condition of a complex sample environment. Compared with other models, our method has advantages in accuracy, training loss, and cost time. Comprehensive comparisons show effectiveness and improved overall performance.

Förderung

  • Civil Aviation Education Talent Foundation
  • Autonomous Project of Sichuan Key Laboratory of Civil Aircraft Fire Science and Safety Engineering
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Li, H., & Sun, P. (2023). Image-Based Fire Detection Using Dynamic Threshold Grayscale Segmentation and Residual Network Transfer Learning. Mathematics, 11(18), 3940. https://doi.org/10.3390/math11183940

Vancouver

Li H, Sun P. Image-Based Fire Detection Using Dynamic Threshold Grayscale Segmentation and Residual Network Transfer Learning. Mathematics. 2023;11(18):3940. doi:10.3390/math11183940

BibTeX
@article{Li2023,
  author = {Li, Hai and Sun, Peng},
  title = {Image-Based Fire Detection Using Dynamic Threshold Grayscale Segmentation and Residual Network Transfer Learning},
  journal = {Mathematics},
  year = {2023},
  volume = {11},
  number = {18},
  pages = {3940},
  doi = {10.3390/math11183940}
}
Kostenlos starten →