Abstract:
Distracted driving is one of the major reason of accidents in the world in which driver is
indulged in other activities and is driving abstractedly which may lead to accident. Many drivers are overconfident and are ignorant of their bad driving habits. In order to aware the drivers of their habits the classification of their behavior and emotional states can play a vital role. If the drivers driving behaviors are identified automatically, the drivers can be conscious of their bad habits which can help them to avoid vehicle accidents. Many researches have suggested many methods or techniques that can be helpful in determining driver's behavior but there is no comprehensive method existed that can cater almost all types of distractions which can occur while driving. In this paper the emotional as well as behavioral distraction states of the driver are analyzed and classified using advance deep learning techniques like convolutional neural
networks and visual geometry group (VGG16). The results show an accuracy of 99% using CNN on the dataset of state farm distracted driver detection. The handling of the emotional and behavioral states simultaneously can be helpful in developing a comprehensive driver's detection system in an efficient manner addressing the previous limitations or challenges that are needed to be solved. This system can be integrated with the self-driving vehicle systems or vehicle security systems in future.
