Detecting and Alerting Driver’s Drowsines Using Deep Learning Techniques

The majority of accidents were caused by drivers who were intoxicated at the time. Despite the Department of numerous sleepiness detection s system over the past ten years, there is still potential for advancement in terms of the systems’ effectiveness, accuracy, affordability, speed, and availability, among other closures. The new proposed vector FCR and the eye and mouth closure state (PERCLOS), similar to ECR and MCR, are determined by the proposed integrated technique that is presented in this work (Facial Closure Ratio). This aids in determining the status of closed eyes or an opening mouth, such as when yawning, as well as any frames that include hand motion like nodding or covering an open mouth with the hand as part of a human's intrinsic ability to manage tiredness. The system also integrated techniques for recognizing the driver's sunglasses, and it recognized and treated situations when the driver had their hands on their mouth or eyes while nodding or yawning. NTHU-DDD, YawDD, and a planned dataset termed EMOCDS were among the datasets tested (Eye and Mouth Open Close Data Set). The proposed work scored higher in terms of accuracy and provided results generally by taking numerous factors into account.