EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RMTSE: A Spatial-Channel Dual Attention Network for Driver Distraction Recognition

Junyi He, Chang Li, Yang Xie, Haotian Luo, Wei Zheng, Yiqun Wang

Sensors · 2025

DOI: 10.3390/s25092821 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Junyi He und 5 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Information Science, Huxi Campus, Chongqing University, Chongqing 400044, China. Hauptthemen laut MEDLINE: Attention, Automobile Driving, Distracted Driving. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chongqing Natural Science Foundation Innovation and Development Joint, Chongqing Natural Science Foundation Innovation and Development Joint Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Driver distraction has become a critical factor in traffic accidents, necessitating accurate behavior recognition for road safety. However, existing methods still suffer from limitations such as low accuracy in recognizing drivers’ localized actions and difficulties in distinguishing subtle differences between different behaviors. This paper proposes RMTSE, a hybrid attention model, to enhance driver distraction recognition. The framework introduces a Manhattan Self-Attention Squeeze-and-Excitation (MaSA-SE) module that combines spatial self-attention with channel attention mechanisms. This integration enables simultaneous enhancement of discriminative features and suppression of irrelevant characteristics in driving behavior images, improving learning efficiency through focused feature extraction. We also propose to employ a transfer learning strategy utilizing pre-trained weights during the training process, which further accelerates model convergence and enhances feature generalization. The model achieves Top-1 accuracies of 99.82% and 94.95% on SFD3 and 100-Driver datasets, respectively, with minimal parameter increments, outperforming existing state-of-the-art methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AttentionAutomobile DrivingDistracted DrivingHumansAlgorithmsAccidents, TrafficNeural Networks, Computer

Stichwörter der Autor:innen

channel attention mechanismdriver distraction recognitiontransfer learningvision transformer

Autor:innen und Institutionen

  • Faculty of Information Science, Huxi Campus, Chongqing University, Chongqing 400044, China.
  • State Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing 400023, China.

Förderung

  • Chongqing Natural Science Foundation Innovation and Development Joint
  • Chongqing Natural Science Foundation Innovation and Development Joint Fund

Zitieren

APA

He, J., Li, C., Xie, Y., Luo, H., Zheng, W., & Wang, Y. (2025). RMTSE: A Spatial-Channel Dual Attention Network for Driver Distraction Recognition. Sensors. https://doi.org/10.3390/s25092821

Vancouver

He J, Li C, Xie Y, Luo H, Zheng W, Wang Y. RMTSE: A Spatial-Channel Dual Attention Network for Driver Distraction Recognition. Sensors. 2025. doi:10.3390/s25092821

BibTeX
@article{He2025,
  author = {He, Junyi and Li, Chang and Xie, Yang and Luo, Haotian and Zheng, Wei and Wang, Yiqun},
  title = {RMTSE: A Spatial-Channel Dual Attention Network for Driver Distraction Recognition},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25092821}
}
Kostenlos starten →