A CNN-Based Wearable System for Driver Drowsiness Detection
Drowsiness poses a serious challenge to road safety and various in-cabin sensing technologies have been experimented with to monitor driver alertness. Cameras offer a convenient means for contactless sensing, but they may violate user privacy and require complex algorithms to accommodate user (e.g.,...
| Main Authors: | , , , , , , |
|---|---|
| 格式: | 文件 |
| 语言: | English |
| 出版: |
MDPI AG
2023-03-01
|
| 丛编: | Sensors |
| 主题: | |
| 在线阅读: | https://www.mdpi.com/1424-8220/23/7/3475 |
| _version_ | 1827746484878049280 |
|---|---|
| author | Yongkai Li Shuai Zhang Gancheng Zhu Zehao Huang Rong Wang Xiaoting Duan Zhiguo Wang |
| author_facet | Yongkai Li Shuai Zhang Gancheng Zhu Zehao Huang Rong Wang Xiaoting Duan Zhiguo Wang |
| author_sort | Yongkai Li |
| collection | DOAJ |
| description | Drowsiness poses a serious challenge to road safety and various in-cabin sensing technologies have been experimented with to monitor driver alertness. Cameras offer a convenient means for contactless sensing, but they may violate user privacy and require complex algorithms to accommodate user (e.g., sunglasses) and environmental (e.g., lighting conditions) constraints. This paper presents a lightweight convolution neural network that measures eye closure based on eye images captured by a wearable glass prototype, which features a hot mirror-based design that allows the camera to be installed on the glass temples. The experimental results showed that the wearable glass prototype, with the neural network in its core, was highly effective in detecting eye blinks. The blink rate derived from the glass output was highly consistent with an industrial gold standard EyeLink eye-tracker. As eye blink characteristics are sensitive measures of driver drowsiness, the glass prototype and the lightweight neural network presented in this paper would provide a computationally efficient yet viable solution for real-world applications. |
| first_indexed | 2024-03-11T05:25:01Z |
| format | Article |
| id | doaj.art-a2cfbe64a9fd4c97bda96b4ce68d8827 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:25:01Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a2cfbe64a9fd4c97bda96b4ce68d88272023-11-17T17:33:04ZengMDPI AGSensors1424-82202023-03-01237347510.3390/s23073475A CNN-Based Wearable System for Driver Drowsiness DetectionYongkai Li0Shuai Zhang1Gancheng Zhu2Zehao Huang3Rong Wang4Xiaoting Duan5Zhiguo Wang6Center for Psychological Sciences, Zhejiang University, Hangzhou 310028, ChinaCenter for Psychological Sciences, Zhejiang University, Hangzhou 310028, ChinaCenter for Psychological Sciences, Zhejiang University, Hangzhou 310028, ChinaCenter for Psychological Sciences, Zhejiang University, Hangzhou 310028, ChinaCenter for Psychological Sciences, Zhejiang University, Hangzhou 310028, ChinaCenter for Psychological Sciences, Zhejiang University, Hangzhou 310028, ChinaCenter for Psychological Sciences, Zhejiang University, Hangzhou 310028, ChinaDrowsiness poses a serious challenge to road safety and various in-cabin sensing technologies have been experimented with to monitor driver alertness. Cameras offer a convenient means for contactless sensing, but they may violate user privacy and require complex algorithms to accommodate user (e.g., sunglasses) and environmental (e.g., lighting conditions) constraints. This paper presents a lightweight convolution neural network that measures eye closure based on eye images captured by a wearable glass prototype, which features a hot mirror-based design that allows the camera to be installed on the glass temples. The experimental results showed that the wearable glass prototype, with the neural network in its core, was highly effective in detecting eye blinks. The blink rate derived from the glass output was highly consistent with an industrial gold standard EyeLink eye-tracker. As eye blink characteristics are sensitive measures of driver drowsiness, the glass prototype and the lightweight neural network presented in this paper would provide a computationally efficient yet viable solution for real-world applications.https://www.mdpi.com/1424-8220/23/7/3475drowsiness detectionglasslightweightdrivingconvolution neural network |
| spellingShingle | Yongkai Li Shuai Zhang Gancheng Zhu Zehao Huang Rong Wang Xiaoting Duan Zhiguo Wang A CNN-Based Wearable System for Driver Drowsiness Detection Sensors drowsiness detection glass lightweight driving convolution neural network |
| title | A CNN-Based Wearable System for Driver Drowsiness Detection |
| title_full | A CNN-Based Wearable System for Driver Drowsiness Detection |
| title_fullStr | A CNN-Based Wearable System for Driver Drowsiness Detection |
| title_full_unstemmed | A CNN-Based Wearable System for Driver Drowsiness Detection |
| title_short | A CNN-Based Wearable System for Driver Drowsiness Detection |
| title_sort | cnn based wearable system for driver drowsiness detection |
| topic | drowsiness detection glass lightweight driving convolution neural network |
| url | https://www.mdpi.com/1424-8220/23/7/3475 |
| work_keys_str_mv | AT yongkaili acnnbasedwearablesystemfordriverdrowsinessdetection AT shuaizhang acnnbasedwearablesystemfordriverdrowsinessdetection AT ganchengzhu acnnbasedwearablesystemfordriverdrowsinessdetection AT zehaohuang acnnbasedwearablesystemfordriverdrowsinessdetection AT rongwang acnnbasedwearablesystemfordriverdrowsinessdetection AT xiaotingduan acnnbasedwearablesystemfordriverdrowsinessdetection AT zhiguowang acnnbasedwearablesystemfordriverdrowsinessdetection AT yongkaili cnnbasedwearablesystemfordriverdrowsinessdetection AT shuaizhang cnnbasedwearablesystemfordriverdrowsinessdetection AT ganchengzhu cnnbasedwearablesystemfordriverdrowsinessdetection AT zehaohuang cnnbasedwearablesystemfordriverdrowsinessdetection AT rongwang cnnbasedwearablesystemfordriverdrowsinessdetection AT xiaotingduan cnnbasedwearablesystemfordriverdrowsinessdetection AT zhiguowang cnnbasedwearablesystemfordriverdrowsinessdetection |