EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Model Lightweighting for Real-time Distraction Detection on Resource-Limited Devices

Jing Wang iD, ZhongCheng Wu

Computational Intelligence and Neuroscience · 23.12.2022 · 2022 · 1-13

DOI: 10.1155/2022/7360170 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Intelligence and Neuroscience, erschienen am 23.12.2022. Verfasst von Jing Wang und 1 weiteren Autor:innen. Beteiligte Einrichtung: High Magnetic Field Laboratory, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China. Hauptthemen laut MEDLINE: Automobile Driving. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shared Data Center and Cloud Service Platform of the Internet of Vehicles, High Magnetic Field Laboratory.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Detecting distracted driving accurately and quickly with limited resources is an essential yet underexplored problem. Most of the existing works ignore the resource-limited reality. In this work, we aim to achieve accurate and fast distracted driver detection in the context of embedded devices where only limited memory and computing resources are available. Specifically, we propose a novel convolutional neural network (CNN) light-weighting method via adjusting block layers and shrinking network channels without compromising the model’s accuracy. Finally, the model is deployed on multiple devices with real-time detection of driving behaviour. The experimental results for the American University in Cairo (AUC) and StateFarm datasets demonstrate the effectiveness of the proposed method. For instance, for the AUC dataset, the proposed MobileNetV2-tiny model achieves 1.63% higher accuracy with just 78% of the model parameters of the original MobileNetV2 model. The inference speed of the proposed MobileNetV2-tiny model on resource-limited devices is on average 1.5 times that of the original MobileNetV2 model, which can meet real-time requirements.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Automobile DrivingHumansNeural Networks, ComputerUniversities

Autor:innen und Institutionen

  • High Magnetic Field Laboratory, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China.
  • University of Science and Technology of China, Hefei 230026, China.

ORCID-Profile: Jing Wang

Förderung

  • Shared Data Center and Cloud Service Platform of the Internet of Vehicles
  • High Magnetic Field Laboratory

Zitieren

APA

Wang, J., & Wu, Z. (2022). Model Lightweighting for Real-time Distraction Detection on Resource-Limited Devices. Computational Intelligence and Neuroscience, 2022, 1-13. https://doi.org/10.1155/2022/7360170

Vancouver

Wang J, Wu Z. Model Lightweighting for Real-time Distraction Detection on Resource-Limited Devices. Computational Intelligence and Neuroscience. 2022;2022:1-13. doi:10.1155/2022/7360170

BibTeX
@article{Wang2022,
  author = {Wang, Jing and Wu, ZhongCheng},
  title = {Model Lightweighting for Real-time Distraction Detection on Resource-Limited Devices},
  journal = {Computational Intelligence and Neuroscience},
  year = {2022},
  volume = {2022},
  pages = {1--13},
  doi = {10.1155/2022/7360170}
}
Kostenlos starten →