REAL TIME DROWSINESS DETECTION

Computer Science and Engineering

Every year, many individuals die as a result of deadly traffic accidents and sleepy driving around the world. One of the leading causes of traffic accidents and deaths is driving. NHTSA estimates that drowsiness contributes to more than 100,000 collisions each year, resulting in over 1,500 deaths and 40,000 injuries. Drowsiness increases the impairment caused by alcohol. Teenagers, professional drivers (including truck drivers), military personnel on leave, and shift workers are at particular risk. Fatigue and micro sleep at the driving controls are often the root cause of serious accidents. Initial indicators of fatigue can be identified before a crucial situation occurs, allowing for the detection of driver fatigue and other issues. Its significance is a study topic that is currently being investigated. Most of the traditional methods to detect drowsiness are based on behavioral aspects while some are intrusive and may distract drivers, while some require expensive sensors. As a result, in this paper, a simple, real-time sleepiness detection system for drivers is created and deployed on an Android application. As a result, in this paper, a simple, real-time sleepiness detection system for drivers is created and deployed on an Android application. The system records the videos and detects driver’s face in every frame by employing image processing techniques. The system is capable of detecting facial landmarks and computes Eye Aspect Ratio (EAR) to detect driver’s drowsiness based on adaptive thresholding.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.