Driver Assistant System using Haar Cascade and Convolution Neural Networks(CNN)

The increasing number of road crashes in which drivers are involved in has created an increased concern. It has been observed that the majority of the crashes arise from errors of attention, breaking signals, drowsiness, talking on mobile phone, etc. The aim of this work is to create a system which will help to assist in controlling such errors and preventing crashes. The proposed system uses machine learning algorithms to detect the state of the driver based on which decisions are made on whether the driver should drive the vehicle or not. First, the detection of the facial features of the driver is done using a camera(place in front of the driver) and image processing. After capturing the features they are fed to a trained neural model to obtain driver state. Haar cascade to detect drowsiness and attention of the driver. Further, to detect if the driver is using a mobile phone Convolutional Neural Network (CNN) was used.