Real-Time Driver Drowsiness Detection System Using Dlib based on Driver Eye/Mouth Monitoring Technology

The driver sleepiness is common and one of the main causes road accidents. So, there a need for automatically detecting this human behaviour. In any case, if drivers feel drowsy, they still keep on driving vehicle, accidents occur. This study can be implemented using CNN training model initiating an alarm drowsiness condition detected. Many authors suggested process Drowsiness (Problem Statement) technologies like Internet Things (IoT), Deep learning, Haar cascade (to detect coordinates eyes mouth, which are target objects). However, contributes towards providing real-time application in co-operating Dlib. Hence, proposes novel embedded system with technology. fed inputs based four (4) images related to eye mouth openings closings. trained model, takes as processes by identifying features face Dlib library while representing change state Yawning. approach achieved Convolution Neural Network (CNN), pillow, Pygame, OpenCV, Dlib, along when position changes. recorded maximum validation accuracy 98% minimum loss less than 0.04% areal-time application.