Enhanced Driver Drowsiness Detection using Deep Learning

The primary reason for road accidents is drowsiness reported by National Highway Traffic Safety Administration (NHTSA). To overcome this issue, researchers have proposed and implemented various methods based on driver behaviour vehicle movements. Vehicle-based often rely a set of predetermined parameters to detect drowsiness, such as changes in steering wheel angle or lane deviation. However, these may not always accurately reflect driver’s level alertness. Therefore, it essential develop an effective approach detection. Deep learning techniques convolutional neural networks (CNN) are structured solutions drivers’ facial features. CNN focuses the eyes mouth region using nose central point. operated with rectified linear activation function (ReLU) which gives 94.95% accuracy compared existing even different situations namely low light, angles, transparent glasses.