Driver-Drowsiness Detection System Using Facial Features

Aim:

This paper aim to detect Real time driver’s fatigue state using Convolutional Neural Network (CNN)

Synopsis:

          Accidents are more due to the driver’s drowsiness; it has been recorded that more than 40% of chances that accidents occur while the driver’s is in drowsiness state. It’s very important that the driver must be in alert state while driving the car. Few methods are intrusive and distract the driver, some require expensive sensors and data handling. Therefore, in Existing study, a low cost, real time driver’s drowsiness detection system is developed with acceptable accuracy. Facial landmarks on the detected face are pointed and subsequently the eye aspect ratio and mouth opening ratio are computed and depending on their values, drowsiness is detected based on developed adaptive thresholding. In the proposed system, a webcam records the video and driver’s face is detected in each frame employing image processing techniques. A novel system for evaluating the driver’s level of fatigue based on face tracking and facial key point detection. In order to track the driver’s face using CNN (Convolution Neural Network) and then the facial regions of detection based on facial key points. Then the eyes and mouth will be detected if the eye is closed the alert system will be displayed.

Proposed System:

         In modern days, we see how car accidents are increasing due to many reasons like drowsy driving or drunk driving or speeding and many more reasons. Hence we develop a modern solution, were my system will alert the driver if driver is sleeping. In the proposed system, a webcam records the video and driver’s face is detected in each frame for image processing techniques. A novel system for evaluating the driver’s level of fatigue based on face tracking and facial key point detection. In order to track the driver’s face using CNN (Convolution Neural Network) and then the facial regions of detection based on facial key points. Then the eyes and mouth will be detected if the eye is closed the alert system will be displayed.