DrowsiScan: Early Detection of Driver Drowsiness using Deep Learning

In recent years, the rise in car accident fatalities has become a significant global concern, with road security emerging as a critical issue. Among the various factors contributing to road accidents, driver drowsiness stands out as a leading cause. This project aims to address this issue by developing a real-time driver drowsiness detection system using advanced machine vision techniques and deep learning models. Drowsy Driver Detection System has been developed using a non- intrusive machine vision based concepts. The system uses a small snap security camera that points directly towards the driver’s face and monitors the driver eyes in order to descry fatigue. In such a case when fatigue is detected, a warning signal is issued to warn the driver. This report describes how to detect the eyes, and also how to determine if the eyes are open state or close state. The algorithm developed is unique to any presently published papers, which was a primary ideal objective of the project. The system deals with using information attained for the double interpretation of the image to find the edges of the face, which narrows the area of where the eyes located. Once the face is detected, the eyes are found by computing the horizontal averages in the area. Taking into account the knowledge that eye regions in the face present great intensity changes, the eyes are located by chancing the significant intensity changes in the face. Once the eyes are located, measuring the distances between the intensity changes in the eye area determine whether the eyes are in open state or close state.A large distance corresponds to eye check. still, the system draws the conclusion that the driver is falling asleep and issues a warning signal, If the eyes are set up closed for 5 successive frames. The system is also suitable to detect when the eyes can not be set up, and works under reasonable lighting conditions.