Abstract:

One of the main factors contributing to traffic mishaps all over the globe is driver fatigue. Driver drowsiness must be detected in real-time in order to avoid such mishaps. Using machine learning, we suggest a method in this article for detecting driving drowsiness. Our system takes a picture of the driver's face with a camera, analyses it using a machine learning programme, and then calculates the driver's degree of sleepiness. Our machine learning model was trained using a sample of motorists who were at various stages of sleepiness. We extracted facial features such as eye closure, mouth opening, and head movement, which are strong indicators of drowsiness. The extracted features were used to train a deep learning model using convolutional neural networks (CNNs). The proposed system achieved an accuracy of 95% in detecting driver drowsiness. We tested our system in real- world scenarios, and the results show that our system can accurately detect driver drowsiness in real-time. Our system has the potential to be integrated into existing advanced driver assistance systems (ADAS) and provide real-time alerts to the driver to take a break or rest. This can greatly lower the number of mishaps brought on by drowsy driving.

Description:

machine learning, Deep learning, Convolution Neural Networks, Facial features, Real-time detection