In this project a hybrid deep learning tool is utilized to detect up to nine various distracted driver activities including driving, drinking, texting, smoking, talking with rising hands, adjusting the navigation system, looking outside, nodding off to sleep, fainting inside a real vehicle cabin during the daytime and nighttime conditions. The developed model is integrated with an alert system in a real vehicles and tested to give a real-time warning system when the drivers engage in distraction activities while driving.
