Behavior Based Human Driver Fatigue Detection System Using Deep Learning

Behavior Based Human Driver Fatigue Detection System Using Deep Learning

Harsh Garud, Swayam Khobragade, Shubham Vhatkar, Ketan Patil, Prof. Pooja V. Baravkar

Department of Computer Engineering

Smt. Kashibai Navale College of Engineering,

Pune, India

Abstract - The "Driver Fatigue Detection System Using Deep Learning" project is an innovative initiative that aims to improve road safety by utilizing advanced technology. It addresses the problem of accidents caused by driver fatigue, which leads to numerous injuries and fatalities each year. The project focuses on developing a smart real-time monitoring system that employs deep learning algorithms to identify and counteract driver fatigue. This system uses sophisticated deep learning techniques, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks, to process a variety of data sources such as in-cabin camera feeds, vehicle performance metrics, and biometric data like eye movements and facial expressions. By analyzing this data, the system can accurately determine the driver's level of alertness and detect signs of fatigue. The key components of the system involve data preprocessing, extracting relevant features, training the model, and providing real-time alerts. When significant indicators of fatigue are detected, the system immediately issues alerts, such as audio warnings or adjustments to adaptive cruise control, to help the driver regain focus and prevent accidents caused by fatigue. This project not only showcases the adaptability of deep learning but also highlights its potential to revolutionize driver monitoring, thereby significantly improving road safety.

Keywords: Fatigue Detection, Audio Warning, Safety.