An embedded intelligence engine for driver drowsiness detection
Abstract Motor vehicle crashes involving drowsy driving are huge in number all over the world. Many studies revealed that 10%–30% of crashes are due to drowsy driving. Fatigue has costly effects on the safety, health, and quality of life. This drowsiness of drivers can be detected using various meth...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi-IET
2022-01-01
|
| Series: | IET Computers & Digital Techniques |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cdt2.12036 |
| _version_ | 1827079672793399296 |
|---|---|
| author | Shirisha Vadlamudi Ali Ahmadinia |
| author_facet | Shirisha Vadlamudi Ali Ahmadinia |
| author_sort | Shirisha Vadlamudi |
| collection | DOAJ |
| description | Abstract Motor vehicle crashes involving drowsy driving are huge in number all over the world. Many studies revealed that 10%–30% of crashes are due to drowsy driving. Fatigue has costly effects on the safety, health, and quality of life. This drowsiness of drivers can be detected using various methods, for example, algorithms based on behavioural gestures, physiological signals and vitals. Also, few of them are vehicle based. Drowsiness of drivers was detected based on steering wheel movement and lane change patterns. A pattern is derived based on slow drifting and fast corrective steering movement. A prototype that detects the drowsiness of an automobile driver using artificial intelligence techniques, precisely using open‐source tools like TensorFlow Lite on a Raspberry Pi development board, is developed. The TensorFlow model is trained on images captured from the video with the help of object detection using cascade classifier. In order to have a better accuracy, an Inception v3 architecture is used in pre‐training the model with the image dataset. The final model is created and trained using long short‐term memory and then the final TensorFlow model is converted to TensorFlow Lite model and this Lite model is used on Raspberry Pi board to detect the drowsiness of drivers. The results are comparable with desktop‐based results in the literature. |
| first_indexed | 2024-03-09T09:34:27Z |
| format | Article |
| id | doaj.art-07a80a48809a478ba30c0b530254ca4d |
| institution | Directory Open Access Journal |
| issn | 1751-8601 1751-861X |
| language | English |
| last_indexed | 2025-03-20T02:49:17Z |
| publishDate | 2022-01-01 |
| publisher | Hindawi-IET |
| record_format | Article |
| series | IET Computers & Digital Techniques |
| spelling | doaj.art-07a80a48809a478ba30c0b530254ca4d2024-10-03T07:27:43ZengHindawi-IETIET Computers & Digital Techniques1751-86011751-861X2022-01-01161101810.1049/cdt2.12036An embedded intelligence engine for driver drowsiness detectionShirisha Vadlamudi0Ali Ahmadinia1Department of Computer Science and Information Systems California State University San Marcos San Marcos California USADepartment of Computer Science and Information Systems California State University San Marcos San Marcos California USAAbstract Motor vehicle crashes involving drowsy driving are huge in number all over the world. Many studies revealed that 10%–30% of crashes are due to drowsy driving. Fatigue has costly effects on the safety, health, and quality of life. This drowsiness of drivers can be detected using various methods, for example, algorithms based on behavioural gestures, physiological signals and vitals. Also, few of them are vehicle based. Drowsiness of drivers was detected based on steering wheel movement and lane change patterns. A pattern is derived based on slow drifting and fast corrective steering movement. A prototype that detects the drowsiness of an automobile driver using artificial intelligence techniques, precisely using open‐source tools like TensorFlow Lite on a Raspberry Pi development board, is developed. The TensorFlow model is trained on images captured from the video with the help of object detection using cascade classifier. In order to have a better accuracy, an Inception v3 architecture is used in pre‐training the model with the image dataset. The final model is created and trained using long short‐term memory and then the final TensorFlow model is converted to TensorFlow Lite model and this Lite model is used on Raspberry Pi board to detect the drowsiness of drivers. The results are comparable with desktop‐based results in the literature.https://doi.org/10.1049/cdt2.12036driver drowsiness detectionembedded intelligenceembedded vision systems |
| spellingShingle | Shirisha Vadlamudi Ali Ahmadinia An embedded intelligence engine for driver drowsiness detection IET Computers & Digital Techniques driver drowsiness detection embedded intelligence embedded vision systems |
| title | An embedded intelligence engine for driver drowsiness detection |
| title_full | An embedded intelligence engine for driver drowsiness detection |
| title_fullStr | An embedded intelligence engine for driver drowsiness detection |
| title_full_unstemmed | An embedded intelligence engine for driver drowsiness detection |
| title_short | An embedded intelligence engine for driver drowsiness detection |
| title_sort | embedded intelligence engine for driver drowsiness detection |
| topic | driver drowsiness detection embedded intelligence embedded vision systems |
| url | https://doi.org/10.1049/cdt2.12036 |
| work_keys_str_mv | AT shirishavadlamudi anembeddedintelligenceenginefordriverdrowsinessdetection AT aliahmadinia anembeddedintelligenceenginefordriverdrowsinessdetection AT shirishavadlamudi embeddedintelligenceenginefordriverdrowsinessdetection AT aliahmadinia embeddedintelligenceenginefordriverdrowsinessdetection |