Recent researches and surveys have provided us with the evidence that distracted driving is a major cause of vehicle crashes all around the world. In-vehicle information systems (IVIS) have raised driver safety concern and thus, detecting distracted driver is of paramount importance. The project (or paper) shows a method of real-time distraction detection and initiates safety measures. In the realization of this project we have used Web-Cam, Raspberry Pi (a low cost, small size computing device), along with concepts of deep learning and convolutional neural networks. We classify drivers into multiple categories of distraction, some of them are texting, drinking, operating IVIS etc. Web-Cam feeds the classifier with real-time images of a driver of a particular vehicle. The system also constitutes a buzzer alarm which rings once the distraction is detected.