A Review on Distracted Driver Detection Using Machine Learning Techniques

Distracted driving is a significant cause of road accidents worldwide, so innovative solutions for effective detection and prevention are needed. This study explores recent advancements in detecting distracted driver methods and compares machine learning (ML), deep learning (DL), and hybrid approaches. It compares various methods, including traditional machine learning, convolutional neural networks (CNNs), and hybrid models. The comparison includes different datasets, such as the State-Farm, AUC, LDDB, and custom distracted driver datasets. The study surveys state-of-the-art methods, datasets, and performance metrics and identifies the strengths and challenges of each approach. The findings emphasize the potential of deep learning to enhance road safety. However, challenges such as high computational costs and the need for real-time applicability remain.