The proposed project addresses the critical issue of driver drowsiness, which is a major cause of accidents on the road. The system utilizes advanced technology, including video image analysis and pressure sensing, to monitor the driver's state while behind the wheel. By detecting the closure of the driver's eyes and measuring the pressure on the steering wheel, the system can accurately determine whether the driver is becoming drowsy or losing focus. The detection of drowsy eyes is particularly crucial, as the duration of eye closure during drowsiness is longer than normal blinking, making it a clear indicator of potential danger. The integration of the pressure sensing system further enhances the accuracy of detecting drowsiness, as it captures instances of loosening grip on the steering wheel, which may signify a decline in attentiveness. This combination of eye and grip monitoring enables the system to issue timely alerts to the driver, warning them to stay alert and avoid potential accidents. Moreover, the ability to detect the presence of hands on the steering wheel also provides an additional layer of safety, ensuring that deliberate actions or distractions are also accounted for. Overall, this comprehensive drowsy eye detection system is seen to be 90% effective in its accuracy which was obtained using F1 score and holds significant social importance by preventing accidents, while also delivering economic benefits through reduced accident-related costs and enhanced overall productivity on the roads.
Guardian Alert: A Deep Learning Approach for Driver Drowsiness Detection and Force Sensing Integration
2023-11-08
1375252 byte
Conference paper
Electronic Resource
English
DDYDAS: Driver Drowsiness, Yawn Detection and Alert System
Springer Verlag | 2021
|Driver Drowsiness Detection Using Deep Learning
IEEE | 2023
|Driver Drowsiness Detection Using Deep Learning
IEEE | 2021
|