A Review of Recent Advancements In The Detection Of Driver Drowsiness

Abstract

This paper overviews the literature on detecting driver drowsiness using behavioral metrics and machine learning approaches. Faces provide information that can be utilized to deduce sleepiness levels. Many facial features can be derived from the face to determine the level of tiredness. Eye blinks, head motions, and yawning are examples of these. The construction of a sleepiness detection system that produces reliable and accurate results, on the other hand, is a complex endeavor that necessitates precise and robust algorithms. In the past, various strategies for detecting driver drowsiness were investigated. The new advent of deep learning necessitates re-evaluating these algorithms' accuracy in detecting tiredness. As a result, this research examines machine learning techniques such as support vector machines, convolutional neural networks, and hidden Markov models in the context of drowsiness detection. Finally, this work provides a list of publicly available datasets that can be utilized as sleepiness detection benchmarks.