Driver Distraction Detection Using Machine Learning

Abstract

The problem of driver distraction has become serious, and this is due to physical distractions that can be dangerous on the roads. Convolutional Neural Networks (CNNs) are used in this research to introduce a new approach to identifying physical distractions. To train the designed CNN model, a large dataset of labeled images that depict different physical distractions such as eating, texting, and manipulating controls is utilized. We make use of the spatial hierarchies learned by CNNs that enable us to extract important information for distraction identification with high efficiency. The experimental results validate the proposed method’s ability to recognize physical distractions in real driving scenarios effectively. Incorporating such models into in-car systems could therefore result in reduced distractions and consequently fewer accidents and additionally offer immediate warnings or interventions thus improving driver safety considerably. Key Words: Distraction, Machine Learning, Convolution Neural Network, Road accidents.