Driver Fatigue Detection Using Multitask Cascaded Convolutional Networks - Intelligence Science I (ICIS 2017) Access content directly
Conference Papers Year : 2017

Driver Fatigue Detection Using Multitask Cascaded Convolutional Networks

Xiaoshuang Liu
  • Function : Author
  • PersonId : 1033374
Zhijun Fang
  • Function : Author
  • PersonId : 1033375
Xiang Liu
  • Function : Author
  • PersonId : 1033376
Xiangxiang Zhang
  • Function : Author
  • PersonId : 1033377
Jianrong Gu
  • Function : Author
  • PersonId : 1033378
Qi Xu
  • Function : Author
  • PersonId : 1033379

Abstract

Driving fatigue is one of the main reasons of traffic accidents. In this paper, we apply the multitask cascaded convolutional networks to face detection and alignment in order to ensure the accuracy and real-time of the algorithm. Afterwards another convolution neural network (CNN) is used for eye state recognition. Finally, we calculate the percentage of eyelid closure (PERCLOS) to detect the fatigue. The experimental results show that the proposed method has high recognition accuracy of eye state and can detect the fatigue effectively in real- time.
Fichier principal
Vignette du fichier
978-3-319-68121-4_15_Chapter.pdf (654.9 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01820907 , version 1 (22-06-2018)

Licence

Attribution

Identifiers

Cite

Xiaoshuang Liu, Zhijun Fang, Xiang Liu, Xiangxiang Zhang, Jianrong Gu, et al.. Driver Fatigue Detection Using Multitask Cascaded Convolutional Networks. 2nd International Conference on Intelligence Science (ICIS), Oct 2017, Shanghai, China. pp.143-152, ⟨10.1007/978-3-319-68121-4_15⟩. ⟨hal-01820907⟩
120 View
185 Download

Altmetric

Share

Gmail Facebook X LinkedIn More