Driver Drowsiness Detection Using YOLO

Driving while fatigued is a severe issue that increases the risk of accidents, injuries, and fatalities. As a response to this problem and to ensure traffic safety, the development of driver sleepiness monitoring systems has attracted great interest. The YOLO (You Only Look Once) algorithm is employed in this study to provide a novel technique for identifying driver intoxication. Many diverse applications use contemporary real-time object identification techniques like YOLO. The proposed system employs the YOLO algorithm to identify and track the driver's face and eyes in real-time video streams captured by an onboard camera. By observing the driver's eyes, the device can accurately detect signs of fatigue such drowsy gaze, blink rate, and eye closure. Using a big dataset of driver photographs with known levels of tiredness, a machine learning model is constructed to enable the system to classify the driver's alertness status in real-time. Experimental results demonstrate the suggested method to be accurate and efficient with a high detection rate and a low false positive rate. The technology can promptly alert the driver when drowsiness is detected, possibly preventing accidents. The suggested approach leverages the YOLO algorithm to detect driver fatigue and offers a reliable and effective solution, increasing overall road safety and reducing the likelihood of accidents caused by fatigued drivers.