Machine learning-based augmented vision for detecting driver drowsiness.
Saved in:
| Title: | Machine learning-based augmented vision for detecting driver drowsiness. |
|---|---|
| Authors: | Ramarao, Gude1 (AUTHOR) ramaraog19@gmail.com, Soni, Palangthod1 (AUTHOR), Vaishnavi, Agraharam Sri1 (AUTHOR), VenkataVarshitha1 (AUTHOR) |
| Source: | Multimedia Tools & Applications. Oct2025, Vol. 84 Issue 33, p41829-41851. 23p. |
| Subjects: | Machine learning, Drowsiness, Convolutional neural networks, Object recognition (Computer vision), Augmented reality, Traffic safety, Wakefulness |
| Abstract: | Fatigued drivers often cause traffic accidents. This study introduces a novel method for detecting fatigue that combines machine learning and image processing techniques. We propose a unique approach that utilizes the Haar Cascade method, the CatBoost algorithm, and an Inception V3 for facial detection and eye classification, allowing for the quick identification and management of drowsiness-related issues. The proposed method uses Haar Cascade for facial detection, proving more reliable than CNN-based methods. A Python-based program detects the real-time images of the driver's face using OpenCV, while deep learning models built on Keras analyze the facial data. The CNN is trained to distinguish between open and closed eyes, aiding in detecting fatigue. When prolonged eye closure is detected, drivers receive immediate advice to stop or take a break. This effort aims to create a fatigue detection system that is both reliable and robust, capable of swiftly identifying prolonged eye closure. Ultimately, our method has the potential to improve road safety significantly and contribute to global initiatives aimed at addressing this critical issue by providing early warnings to drivers. [ABSTRACT FROM AUTHOR] |
| Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Fatigued drivers often cause traffic accidents. This study introduces a novel method for detecting fatigue that combines machine learning and image processing techniques. We propose a unique approach that utilizes the Haar Cascade method, the CatBoost algorithm, and an Inception V3 for facial detection and eye classification, allowing for the quick identification and management of drowsiness-related issues. The proposed method uses Haar Cascade for facial detection, proving more reliable than CNN-based methods. A Python-based program detects the real-time images of the driver's face using OpenCV, while deep learning models built on Keras analyze the facial data. The CNN is trained to distinguish between open and closed eyes, aiding in detecting fatigue. When prolonged eye closure is detected, drivers receive immediate advice to stop or take a break. This effort aims to create a fatigue detection system that is both reliable and robust, capable of swiftly identifying prolonged eye closure. Ultimately, our method has the potential to improve road safety significantly and contribute to global initiatives aimed at addressing this critical issue by providing early warnings to drivers. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 13807501 |
| DOI: | 10.1007/s11042-025-20745-x |
