Driver Drowsiness Detection and Alert System Development Using Object Detection

Fatigue driving is an invisible killer in car accidents and one of the main causes traffic accidents. In order to reduce caused by fatigue, this research has developed a safety assist device prevent such research, non-contact driver drowsiness detection alert system established vehicle cabin. The real-time facial image obtained through camera installed front driver, then input NVIDIA Jetson TX2 embedded module. YOLO (You Only Look Once) object algorithm used detect opening closing driver's eyes, processing eye area, determine whether currently awake or fatigued while driving. can be applied interior environment monitor status. When fatigued, will simultaneously emit sound light signals promptly warn dangerous behaviors. It from continuing drive when ensure safety.