Driver Drowsiness Detection Using Computer Vision and Machine Learning Techniques

It is alarming that car crashes resulting in damage to automobiles, injuries to passengers, and loss of lives occur daily. The incidence of road crashes is rapidly increasing worldwide and has drawn many road safety commissions and concerned individuals to discuss ways to drastically reduce this menacing situation. The introduction of artificial intelligence and technological advancement has prompted government agencies and state commissions to call upon universities and research institutions to develop methods to curb the rise of automobile crashes. These crashes can be attributed to various factors, including drunk driving and, most notably, drowsiness, which affects a wide range of individuals. Drowsiness detection can be categorized into three main techniques; behavioral-based, vehicular-based, and physiological-based. In this research, the behavioral-based approach was studied, with significant consideration being the cost of implementation, execution time, and accuracy. Three machine learning (ML) classifiers were considered: Support Vector Machine (SVM), Naïve Bayes (NB), and Random Forest (RF). A dataset of 1448 images was used for training and testing these classifiers: 70% for training and 30% for testing. Random Forest classifier gave the best accuracy of (92.41) compared to SVM (90.34) and Naïve Bayes (69.43).