• Deep Ruparel
• Abhay Rajde
• Sahil Shah
• Prof..Manya Gidwani

Abstract—The rate of accidents have been increasing at an alarming rate in recent years all around the globe. When trying to find the main reason behind this increasing rate it was found that the majority of the drivers were distracted when driving which caused their accidents. The survey of the National Highway Traffic Safety Administration states that nearly one in five motor vehicle crashes is caused by distracted drivers. We intend to develop a model to successfully identify whether the driver is distracted while driving or is the driver driving safely. In this paper, we try to list down the various approaches of deep learning that were followed by us such as the vgg16 model, mobilenet, sequential model, pre-trained weights of vgg16 model and many more which helped us to develop a model which was able to provide us with promising accuracy and definite results .Experimental results show that our system achieves an accuracy of 93%.

distracted driving, vgg16 model, mobilenet, pretrained vgg16 weights, sequential model, Convolution Neural Networks, Deep Learning

"DISTRACTED DRIVER DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 10, page no.2843-2847, October-2020, Available :http://www.jetir.org/papers/JETIR2010371.pdf

"DISTRACTED DRIVER DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 10, page no. pp2843-2847, October-2020, Available at : http://www.jetir.org/papers/JETIR2010371.pdf