Driver Drowsiness Detection Using Machine Learning

Abstract

 Drowsiness of drivers is one of the significant causes of road accidents. Every year, there is an increase in the amount of deaths and fatal injuries globally. Driving safely depends on ignoring distractions and keeping your eyes on the road. You should take the following actions in order to maintain concentration while driving: Never multitask while driving; pay full attention at all times. Use no electronic devices, including phones, while driving. By detecting the driver’s drowsiness, road accidents can be reduced. This paper describes a machine learning approach for drowsiness detection .Future research will advance the science of machine learning. The challenge of assessing and interpreting the volume of data that is growing so quickly is what has led to this development. The foundation of machine learning is the idea that, with the help of this growing data, the best model for the new data may be found among the old data. Therefore, research into machine learning will continue in tandem with the growth of data. The history of machine learning, the techniques employed, the areas in which it is applied, and the research in this area are all covered in this study. The purpose of this study is to educate academics on machine learning, which has recently gained a lot of popularity, and its applications. Face detection is employed to locate the regions of the driver’s eyes, which are used as the templates for eye tracking. Finally, the tracked eye’s images are used for drowsiness detection in order to generate warning alarms. This proposed approach has three stages: Detecting Face, Detecting Eyes and Detecting Drowsiness .It works by taking images as input from a webcam using the method provided by OpenCV. Then, detect faces in the image and create a Region Of Interest (ROI). Classifier will categorise whether Eyes are open or closed and Calculate Score to check whether Person is Drowsy by comparing it with the threshold value. The model is built with Keras using Convolutional Neural Networks (CNN), Python, HAAR and OpenCV which will alert the driver when he feels sleepy. The average correct rate for eye location and tracking could achieve 95.0% based on some test videos. Thus, the proposed approach for a real-time of driver drowsiness detection is a low cost and effective solution method.