EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Fire Smoke Detection Method Combining a Self-Attention Mechanism and Radial Multi-Scale Feature Connection

Chuan Jin iD, Anqi Zheng, Zhaoying Wu, Changqing Tong

Sensors · 22.03.2023 · 23 (6) · 3358

DOI: 10.3390/s23063358 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.03.2023. Verfasst von Chuan Jin und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Sciences, Hangzhou Dianzi University, Hangzhou 310018, China. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Social Science Fund of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fire remains a pressing issue that requires urgent attention. Due to its uncontrollable and unpredictable nature, it can easily trigger chain reactions and increase the difficulty of extinguishing, posing a significant threat to people’s lives and property. The effectiveness of traditional photoelectric- or ionization-based detectors is inhibited when detecting fire smoke due to the variable shape, characteristics, and scale of the detected objects and the small size of the fire source in the early stages. Additionally, the uneven distribution of fire and smoke and the complexity and variety of the surroundings in which they occur contribute to inconspicuous pixel-level-based feature information, making identification difficult. We propose a real-time fire smoke detection algorithm based on multi-scale feature information and an attention mechanism. Firstly, the feature information layers extracted from the network are fused into a radial connection to enhance the semantic and location information of the features. Secondly, to address the challenge of recognizing harsh fire sources, we designed a permutation self-attention mechanism to concentrate on features in channel and spatial directions to gather contextual information as accurately as possible. Thirdly, we constructed a new feature extraction module to increase the detection efficiency of the network while retaining feature information. Finally, we propose a cross-grid sample matching approach and a weighted decay loss function to handle the issue of imbalanced samples. Our model achieves the best detection results compared to standard detection methods using a handcrafted fire smoke detection dataset, with APval reaching 62.5%, APSval reaching 58.5%, and FPS reaching 113.6.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismcross-grid matching strategyfire smoke detectionmulti-scale featureradial connectionweighted decay

Autor:innen und Institutionen

  • School of Sciences, Hangzhou Dianzi University, Hangzhou 310018, China.
  • Southeast-Monash Joint Graduate School, Southeast University, Suzhou 210096, China.

ORCID-Profile: Chuan Jin

Förderung

  • National Social Science Fund of China

Zitieren

APA

Jin, C., Zheng, A., Wu, Z., & Tong, C. (2023). Real-Time Fire Smoke Detection Method Combining a Self-Attention Mechanism and Radial Multi-Scale Feature Connection. Sensors, 23(6), 3358. https://doi.org/10.3390/s23063358

Vancouver

Jin C, Zheng A, Wu Z, Tong C. Real-Time Fire Smoke Detection Method Combining a Self-Attention Mechanism and Radial Multi-Scale Feature Connection. Sensors. 2023;23(6):3358. doi:10.3390/s23063358

BibTeX
@article{Jin2023,
  author = {Jin, Chuan and Zheng, Anqi and Wu, Zhaoying and Tong, Changqing},
  title = {Real-Time Fire Smoke Detection Method Combining a Self-Attention Mechanism and Radial Multi-Scale Feature Connection},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {6},
  pages = {3358},
  doi = {10.3390/s23063358}
}
Kostenlos starten →