[Paper Review] Driver Drowsiness Detection System: An Approach By Machine Learning Application

Jagbeer Singh, Ritika Kanojia+3 more|arXiv (Cornell University)|Mar 11, 2023

Sleep and Work-Related Fatigue14 citations

TL;DR

The paper proposes a machine learning based system that detects driver drowsiness via face and eye-tracking, matching eye images to a dataset, and sounding alerts when eyes are closed, achieving about 80% accuracy.

ABSTRACT

The majority of human deaths and injuries are caused by traffic accidents. A million people worldwide die each year due to traffic accident injuries, consistent with the World Health Organization. Drivers who do not receive enough sleep, rest, or who feel weary may fall asleep behind the wheel, endangering both themselves and other road users. The research on road accidents specified that major road accidents occur due to drowsiness while driving. These days, it is observed that tired driving is the main reason to occur drowsiness. Now, drowsiness becomes the main principle for to increase in the number of road accidents. This becomes a major issue in a world which is very important to resolve as soon as possible. The predominant goal of all devices is to improve the performance to detect drowsiness in real time. Many devices were developed to detect drowsiness, which depend on different artificial intelligence algorithms. So, our research is also related to driver drowsiness detection which can identify the drowsiness of a driver by identifying the face and then followed by eye tracking. The extracted eye image is matched with the dataset by the system. With the help of the dataset, the system detected that if eyes were close for a certain range, it could ring an alarm to alert the driver and if the eyes were open after the alert, then it could continue tracking. If the eyes were open then the score that we set decreased and if the eyes were closed then the score increased. This paper focus to resolve the problem of drowsiness detection with an accuracy of 80% and helps to reduce road accidents.

Motivation & Objective

• Address the high incidence of road accidents caused by drowsy driving.
• Develop a real-time drowsiness detection approach using facial and eye-tracking cues.
• Evaluate an ML-based system that alarms when eyes remain closed for a threshold.
• Demonstrate a correlation between eye state (open/closed) and drowsiness to reduce accidents.

Proposed method

• Identify the driver's face and track eyes in real time.
• Extract eye images and compare them against a dataset to classify drowsiness.
• Use an eye-closure based scoring mechanism where closed eyes increase a score and open eyes decrease it.
• Trigger an alarm if the eyes remain closed for a configured range.
• Aim for a real-time performance with an accuracy around 80%.

Experimental results

Research questions

• RQ1 Can real-time eye-tracking and facial analysis reliably detect driver drowsiness?
• RQ2 How effective is dataset-based matching of eye images for drowsiness classification?
• RQ3 Does an eye-closure score correlate with drowsiness to trigger timely alerts?

Key findings

• System achieves an accuracy of approximately 80% in detecting drowsiness.
• Alerts are triggered when eyes are closed for a specified duration.
• Eye-state tracking (open vs closed) informs a dynamic scoring mechanism.
• Real-time processing is a focus to promptly notify the driver.
• The approach emphasizes reducing road accidents by early drowsiness detection.