Publications

Abstract : Driver distraction is a foremost cause for motor vehicle accidents and incidents. Driving requires an intensive amount of concentration otherwise the results can be fatal. Yet, most motor vehicles have no system in place to assist the driver when he is feeling drowsy, fatigued or distracted. In this research, we developed a system which detects the driver's drowsiness by using deep learning and computer vision. Whenever the driver is not concentrating, an alarm ring's. Image recognition is made possible through a model called deep convolutional neural networks (CNN). CNN can achieve good performance even on difficult image recognition tasks. Convolutional Neural Networks is a class of artificial neural networks. In this research, we used state of the art model for estimating the position of the face and the eyes to help in the better detection and reduce false positives and false negatives.