Drivers Drowsiness Detection Using Machine Learning

Driver drowsiness is one of the most significant causes of motor vehicle accidents. There is an annual increase in the number of fatalities and fatal injuries worldwide. Driver fatigue is one of the leading factors of automobile accidents. It is a serious road safety issue. If drivers were alerted before they became too sleepy to drive safely, some of these collisions could be avoided. In order to reliably detect drowsiness, it is necessary to provide opportune warnings of drowsiness. To date, slumber detection methods have been ineffective due to their failure to account for individual differences. On the basis of the type of data employed, slumber detection can be conveniently divided into intrusive and non-intrusive methods. During the survey, non-intrusive methods detect drowsiness by measuring driving behavior and occasionally ocular features, with camera-based detection systems being the most effective and therefore useful in real-world driving scenarios. By detecting drowsiness in the motorist, road accidents can be prevented. This paper describes a machine learning method for detecting fatigue. Face detection is used to identify the driver’s eye regions, which are then used as templates for eye tracking in subsequent frames. The monitored eye’s images are used to detect drowsiness in order to generate warning alarms.