A systematic review on analysis of automatic drowsiness detection for preventing road accidents

Fatigue or drowsiness poses a significant threat to road safety and is a major contributor to accidents. Promptly warning drowsy drivers can prevent numerous fatal accidents. Various methods for detecting drowsiness while driving are available, which monitor the driver's level of alertness and sound an alarm if they appear to be losing focus. Facial expressions, such as yawning, eye closure, and head movements, can be analyzed to determine the degree of drowsiness. Drowsiness detection can also be accomplished by evaluating the driver's physical condition and observing the vehicle's actions. In this paper, a thorough examination is presented of the current approaches for detecting driver drowsiness, along with a detailed analysis of the commonly utilized classification methods for this purpose. The paper presents a detailed review of the literature on data collection, drowsiness/fatigue identification systems, analysis of vehicle movements, and physiological changes to detect driver fatigue. The comparative study evaluates the performance of different automatic drowsiness detection technologies, including hybrid and other approaches. Finally, the paper concludes that automatic drowsiness detection technologies have the potential to reduce road accidents caused by driver fatigue. However, the paper also emphasizes the need for further research to develop more accurate and reliable technologies that can work in real-time and under different driving conditions. The paper recommends that a combination of multiple technologies may be the most effective approach for automatic drowsiness detection.