Study on Training Convolutional Neural Network to Detect Distraction and Drowsiness

被引：0

作者：

Kim, Whui ^{[1
]}

Choi, Hyun-Kyun ^{[1
]}

Jang, Byung-Tae ^{[1
]}

机构：

[1] Elect & Telecommun Res Inst, Intelligent Robot Res Div, Daejeon, South Korea

来源：

2018 IEEE REGION TEN SYMPOSIUM (TENSYMP) | 2018年

关键词：

driver monitoring; drowsy; drowsiness; distraction; deeplearning; convolutional neural network; CNN; MobileNet;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Most critical reason of the crash causal chain was caused by the driver. In other to reduce such human factors, it is necessary to use multiple pieces of information acquired by monitoring driver. In this paper, we propose a method to detect both distraction and drowsiness using a single convolutional neural network, and show that data composition should be different depending on the relationship of two or more class properties. In our experiments, we show driver distraction and drowsiness are reliably classified without decreasing accuracy and frames per seconds.

引用

页码：260 / 264

页数：5