International Research Journal of Engineering and Technology (IRJET) Volume: 11 Issue: 06 | Jun 2024 www.irjet.net
e-ISSN: 2395-0056 p-ISSN: 2395-0072
Enhancing Road Safety: A Deep Learning Approach to Detect Driver Drowsiness Prof. A S Phapale1,Atharva Sontakke2,Pranav Mohite3,Siddhi Raina4,Kushagra Shukla5 -------------------------------------------------------------------***----------------------------------------------------------------
Abstract— In modern society, significant shifts in time management have disrupted the natural sleep cycles of individuals. This has led to insufficient rest, resulting in pervasive drowsiness at any given time of the day. The repercussions of this altered sleep pattern are particularly evident in activities demanding heightened alertness, such as driving. Drowsiness has emerged as a major contributor to road accidents, with the Central Road Research Institute (CRRI) attributing approximately 40% of such incidents to fatigued drivers. Recognizing the potential dangers, there is a critical need for interventions to mitigate the risks associated with driver drowsiness. This paper outlines the development of a comprehensive drowsiness detection system that analyzes the driver's eye state to deduce their drowsiness level and issues timely alerts, thus averting potential threats to road safety.
drivers who drive vehicles at night. According to Vandana Saini et. al., around 20% of all accidents are fatigue-related and around 50% on certain roads[1]. So, driver fatigue contributes a significant proportion to all road accidents. Drowsiness is a state of reduced wakefulness and alertness that can lead to a strong desire to fall asleep. It is often characterized by a feeling of fatigue, difficulty concentrating, heavy eyelids, and a decreased ability to perform cognitive and physical tasks effectively. Drowsiness is a natural physiological response to various factors, including inadequate sleep, extended periods of wakefulness, certain medications, and underlying medical conditions. Drowsiness is different from normal tiredness in that it specifically refers to the feeling of being on the verge of falling asleep even when you're trying to stay awake. It can become dangerous if it occurs while performing tasks that require high levels of attention, such as driving or operating heavy machinery, as it can impair reaction times and increase the risk of accidents.
Keywords— Drowsiness Detection, Fatigue Detection, Classification, Driver Monitoring System, Road Safety I. INTRODUCTION Driver fatigue and drowsiness pose significant risks to road safety, contributing to a substantial number of accidents worldwide. Recognizing the critical need to address this issue, the Drowsiness Detection System emerges as a sophisticated solution leveraging cuttingedge technologies. This system combines computer vision and machine learning techniques to monitor drivers in real-time, identifying subtle signs of drowsiness and fatigue. By employing facial recognition and eye-tracking algorithms, the system analyzes key indicators such as eye closure duration and head movements. The objective is to provide an early warning mechanism that prompts drivers to take corrective action, preventing potential accidents caused by impaired alertness. This research contributes to the advancement of intelligent transportation systems, aiming to create a safer driving environment and reduce the incidence of accidents associated with drowsy driving. As the Drowsiness Detection System becomes an integral part of vehicle safety technology, it holds the promise of significantly enhancing road safety and saving lives.
Sleep-deprived drivers responsible for 40% of road accidents, say transport officials . In situations where drowsiness becomes chronic or severely impacts daily functioning, it might be a symptom of a sleep disorder like sleep apnoea, narcolepsy, or insomnia. Addressing the underlying causes of drowsiness is important for maintaining overall well-being and ensuring safety in various activities. II. LITERATURE SURVEY Paper Title- Early Identification and Detection of Driver Drowsiness by Hybrid Machine Learning Description- The research in this field focuses on four types of fatigue detection. The first is made up of the conductors' physiological signals, such as electroencephalogram (EEG), electrocardiograph (ECG), and electrocardiogram (EOG). This category gives good results, but getting these signals is usually very complicated and laborious
Machine learning focuses on the development of models and programs which when provided with data can make observations and learn for themselves. Nowadays we have cameras that produce high-quality images on which the machine learning algorithms can be applied and also we have computation power at our disposal because of which we can apply it to solve real-world problems. In this paper, we propose a practical implementation of these algorithms to build a technology to provide safety to
© 2024, IRJET
|
Impact Factor value: 8.226
Paper IoT-Based Smart Alert System for Drowsy Driver Detection Description-Upon successful integration of the Pi Camera Model V2 with the Raspberry Pi 3, continuous recording of the driver's facial movements is initiated. This research
|
ISO 9001:2008 Certified Journal
|
Page 406