Applying deep neural networks for multi-level classification of driver drowsiness using Vehicle-based measures

作者：

Highlights：

• Deep neural networks improve the accuracy of driver drowsiness detection.

• Different levels of drowsiness are classified using deep convolutional networks.

• Recurrent layers outperform convolutional networks for drowsiness detection.

• Vehicle data are sufficient to have a good accuracy for drowsiness classification.

摘要

•Deep neural networks improve the accuracy of driver drowsiness detection.•Different levels of drowsiness are classified using deep convolutional networks.•Recurrent layers outperform convolutional networks for drowsiness detection.•Vehicle data are sufficient to have a good accuracy for drowsiness classification.

论文关键词：Deep learning,Driver drowsiness detection,Recurrent convolutional networks,Vehicle-based data

论文评审过程：Received 3 August 2019, Revised 30 May 2020, Accepted 17 July 2020, Available online 25 July 2020, Version of Record 31 July 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113778