Driver Fatigue Detection Method

In recent years,various studies have shown that driver’s fatigue is one of the main causes of road accidents in the world and can lead to severe physical injuries,deaths and significant economic losses.Statistics show the need for a reliable driver fatigue detection system,which can alert the driver before a mishap takes place.A direct way to measure the driver’s fatigue is by measuring the driver’s condition,that is,drowsiness.Therefore,it is very important to detect the drowsiness of the driver to save life and property.The advances in technologies to prevent drowsiness at the time is a serious problem in the field of accident prevention.Progress in computer technology has provided the means to create intelligent vehicle systems.Drowsiness especially on long trips,play a key role in traffic accidents.This study introduces a new module for automatic drowsiness detection of drivers based on visual information and artificial intelligence.The purpose of this system is to find,track and analyze the driver’s face and eyes to calculate the drowsiness index to avoid accidents.Both face detection and eye detection are performed using the Haar-like features and AdaBoost classifiers.To achieve greater accuracy when tracking a face,we propose a new method,which is consists of detection and tracking of objects.The proposed method of face tracking also has the ability of self-correction.After the eye region is detected,the local binary pattern(LBP)is used to extract the characteristics of the eyes.Using these characteristics,the Support Vector Machine(SVM)classifier was prepared for the analysis of the eye condition.The refinement of the algorithm more accurately determines the level of drowsiness by implementing a support vector machine classification for a reliable and precise drowsiness warning system.In experiment video,we were able to track the face with a precision of 99%and detecting eye blink by the accuracy of 98.4%.Finally,we can decide on the drowsiness and distraction of the driver.This detection system provides a non-contact technique for assessing the different levels of driver readiness and facilitates early detection of reduced readiness while driving.The experimental results show high precision in each section,which makes this system reliable for detecting drowsiness of the driver.After this,a number of road accidents can be avoided if a warning is sent to the driver who is considered sleepy.