Driver Drowsiness Detection System

Year : 2025 | Volume : 03 | Issue : 02 | Page : 16 21
    By

    Suchi Pandey,

  • Anup Kumar,

  • Abushahama Khan,

  • Jakariya Khan,

  1. Assistant Professor, Department of Computer Science- Artificial Intelligence and Machine Learning, Bansal Institute of Engineering and Technology, Lucknow, India
  2. Student, Department of Computer Science- Artificial Intelligence and Machine Learning, Bansal Institute of Engineering and Technology, Lucknow, India
  3. Student, Department of Computer Science- Artificial Intelligence and Machine Learning, Bansal Institute of Engineering and Technology, Lucknow, India
  4. Student, Department of Computer Science- Artificial Intelligence and Machine Learning, Bansal Institute of Engineering and Technology, Lucknow, India

Abstract

One of the main causes of road accidents worldwide in recent years is driver fatigue. Assessing a driver’s mood, or how sleepy they are, is a clear approach to gauge their level of exhaustion. Therefore, detecting driver fatigue is very important to save lives and property. The creation of a prototype drowsiness detection system is the aim of this research. The system operates in real time, continuously capturing images and measuring the eye’s condition based on a given algorithm, issuing warnings when ne cessary. Since driver weariness is one of the main causes of traffic accidents globally, monitoring driver drowsiness is crucial to maintaining road safety. Although there are various techniques available to detect drowsiness—such as wearable sensors, steering behavior analysis, and physiological signal monitoring, many of these methods are invasive or uncomfortable for the driver. In contrast, the approach implemented in this project is entirely non-invasive, meaning it does not require any physical contact or wearable equipment. This makes it highly user- friendly and allows for more accurate and natural observation of the driver’s behavior without causing any distraction or discomfort. The primary focus of this system is the analysis of the driver’s eye behavior, particularly eye closure. Prolonged eye closure is a strong indicator of fatigue or drowsiness. The device uses real-time video feed to continuously monitor the driver’s eyes. If the eyes remain closed beyond a certain threshold duration or at a high frequency, the system interprets this as a sign of drowsiness and can trigger alerts to regain the driver’s attention. To implement this functionality, advanced computer vision techniques are used, specifically through libraries such as OpenCV and Dlib. In order to determine the Eye Aspect Ratio (EAR), a number that shows whether the eyes are open or closed, and to recognize facial landmarks, these libraries are essential. When the EAR falls below a set limit for a certain number of frames, the system concludes that the driver may be sleepy. This real-time, automated system enhances vehicle safety and reduces the risk of accidents by providing timely alerts. Moreover, it is scalable and can be integrated with other vehicle safety systems. Future developments could incorporate additional features like head pose estimation, yawning detection, and even AI-based fatigue prediction models for more comprehensive monitoring.

Keywords: Driver Drowsiness Detection, Non-Invasive Monitoring, Eye Aspect Ratio (EAR), Computer Vision, OpenCV and Dlib Libraries.

[This article belongs to International Journal of Optical Innovations & Research ]

How to cite this article:
Suchi Pandey, Anup Kumar, Abushahama Khan, Jakariya Khan. Driver Drowsiness Detection System. International Journal of Optical Innovations & Research. 2025; 03(02):16-21.
How to cite this URL:
Suchi Pandey, Anup Kumar, Abushahama Khan, Jakariya Khan. Driver Drowsiness Detection System. International Journal of Optical Innovations & Research. 2025; 03(02):16-21. Available from: https://journals.stmjournals.com/ijoir/article=2025/view=235456


References

  1. Vesselenyi T, Moca S, Rus A, Mitran T, Tătaru B. Driver drowsiness detection using ANN image processing. InIOP conference series: materials science and engineering 2017 Oct 1 (Vol. 252, No. 1, p. 012097). IOP Publishing.
  2. Mehta S, Dadhich S, Gumber S, Jadhav Bhatt A. Real-time driver drowsiness detection system using eye aspect ratio and eye closure ratio. InProceedings of international conference on sustainable computing in science, technology and management (SUSCOM), Amity University Rajasthan, Jaipur-India 2019 Feb 26.
  3. Ahmad K, Em PP, Aziz NA. Machine learning approaches for detecting driver drowsiness: a critical review. International journal of membrane science and technology. 2023 Sep;10(1):329-46.
  4. Gwak J, Hirao A, Shino M. An investigation of early detection of driver drowsiness using ensemble machine learning based on hybrid sensing. Applied Sciences. 2020 Apr 22;10(8):2890.
  5. Kumari K. Review on drowsy driving: Becoming dangerous problem. Int. J. Sci. Res. 2014 Jan;3(1):49-51.
  6. Albadawi Y, Takruri M, Awad M. A review of recent developments in driver drowsiness detection systems. Sensors. 2022 Mar 7;22(5):2069.
  7. Deng W, Wu R. Real-time driver-drowsiness detection system using facial features. Ieee Access. 2019 Aug 21;7:118727-38.
  8. Viola P, Jones M. Rapid object detection using a boosted cascade of simple features. InProceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001 2001 Dec 8 (Vol. 1, pp. I-I). Ieee.
  9. Alshaqaqi B, Baquhaizel AS, Ouis ME, Boumehed M, Ouamri A, Keche M. Driver drowsiness detection system. In2013 8th international workshop on systems, signal processing and their applications (WoSSPA) 2013 May 12 (pp. 151-155). IEEE.
  10. Grace R, Byrne VE, Bierman DM, Legrand JM, Gricourt D, Davis BK, Staszewski JJ, Carnahan B. A drowsy driver detection system for heavy vehicles. In17th DASC. AIAA/IEEE/SAE. Digital Avionics Systems Conference. Proceedings (Cat. No. 98CH36267) 1998 Oct 31 (Vol. 2, pp. I36-1). IEEE.
  11. Malla AM, Davidson PR, Bones PJ, Green R, Jones RD. Automated video- based measurement of eye closure for detecting behavioral microsleep. In2010 annual international conference of the IEEE engineering in medicine and biology 2010 Aug 31 (pp. 6741-6744). IEEE.
Regular Issue Subscription Review Article
Volume 03
Issue 02
Received 24/05/2025
Accepted 09/09/2025
Published 31/12/2025
Publication Time 221 Days
186

Login


My IP

PlumX Metrics