Zhang, H. (2021) Research on Fatigue Driving Detection and Its Early Warning Method Based on Driver Physiological Signals. Master’s Thesis, Jilin University, Changchun.
https://doi.org/10.27162/d.cnki.gjlin.2021.005168

has been cited by the following article:

• TITLE: Intelligent In-Vehicle Safety System Based on Yolov5

  AUTHORS: Biyun Chen, Wei Cai, Jinwen Zhu

  KEYWORDS: Behaviour Detection, STM32, Pyside2, Yolov5, Dlib Open Source Library, Perclos Model

  JOURNAL NAME: Journal of Computer and Communications, Vol.12 No.3, March 28, 2024

  ABSTRACT: In order to reduce the occurrence of traffic accidents and assist drivers to avoid dangerous driving. This paper presents a smart in-vehicle safety system that utilises the Yolov5 algorithm. Yolov5 algorithm is used to anticipate driver fatigue and distraction behaviours, and remind drivers to pay attention to safe driving in time. The system continuously splits the frames and analyses the frame content through the video feedback from the front camera, compared to the traditional machine learning, Yolov5’s mosaic data is enhanced, resulting in a batch size enhancement of 92.3%, and it also uses the Drop Block mechanism to prevent overfitting. The hardware of this system uses STM32 microcontroller and uses system DMA interrupt control and buzzer alarm device to warn about dangerous driving behaviour.