Real-Time Driver Drowsiness Detection Using IoT Device & Detecting Drowsiness Using Machine Learning Techniques

Yawning is a common sign of fatigue or exhaustion among drivers. As part of the framework for screening for driver insufficiency, techniques for a different finding of the driver's yawning have been created. However, accurately detecting a driver's yawning is currently a dangerous task, especially in applications like driver fatigue detection, where lighting conditions can change widely and where a driver's facial features can change in terms of their size, shape, surface, and degree of mutilation. It will be discussed how a large brain network model was created using yawning video cuts for motion gaining and moderate securing, as well as enlarged images for yawning recognition. Therefore, unlike other systems that use a series of cycles to identify faces, coordinate the eyes, nose, and mouth, and confirm that the mouth is open or closed, the proposed yawning discovery framework recognizes yawning occasions directly from video pictures without requiring any facial part positions.
Department Name
Electrical and Computer Engineering
North South University
Printed Thesis