• Nazina . N

The project presents a comprehensive system for real-time detection of driver drowsiness using visual features, addressing a critical road safety issue. It introduces a non-invasive approach that relies on analyzing visual indicators such as facial landmarks, eye, and head movements to predict drowsiness with up to 99% accuracy. Unlike traditional methods that use biological signals or vehicle motion patterns, this system utilizes advanced machine learning techniques, including YOLOv5 for facial feature detection, to improve detection accuracy and speed. The project encompasses a detailed review of existing systems, highlighting their limitations and proposing a more efficient solution. It includes an evaluation of software and hardware requirements, ensuring compatibility with common operating systems and accessibility for real-time applications. A significant portion of the project is dedicated to data collection and algorithm training, focusing on optimizing performance under various conditions. The literature survey and feasibility study underline the project's innovative approach and practicality, aiming to enhance driver safety by providing timely alerts on drowsiness detection.

Drowsiness, message system,accident,message alert

"Driver Drowsiness Detection Using YOLO v5", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.m216-m217, April-2024, Available :http://www.jetir.org/papers/JETIR2404C29.pdf

"Driver Drowsiness Detection Using YOLO v5", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppm216-m217, April-2024, Available at : http://www.jetir.org/papers/JETIR2404C29.pdf