Drowsiness Detection Monitor for Safe driving

PROJECT ID: 24MP03030215

Group Members
RA2011003030215 Ashish Raj
RA2011003030193 Aditi Jha

Supervised By:
Akanksha Bisht
Assistant Professor
Department of Computer Science & Engineering

Faculty of Engineering & Technology

SRM Institute of Science & Technology

July 2024
 ❖ Abstract
❖ Introduction
❖ Literature Review
TABLE OF
❖ Existing System
❖ Proposed System
CONTENTS ❖ System Code
❖ Methodology
❖ References
 ABSTRACT

Drowsy Driving? Say No with the IDM!

Sleepy drivers, beware! This project tackles the growing concern of drowsy driving with the Intelligent Drowsiness Monitor (IDM).
Using advanced sensors and AI, the IDM detects fatigue early and alerts drivers before their eyelids dip. Say goodbye to drowsy-
induced accidents and hello to safer roads for everyone!

How it works:

● Smart sensors: Eyes on the road, not just you! Cameras, brainwave readers (EEGs), and steering sensors track your
alertness level.
● AI detective: Sophisticated algorithms analyze your blinks, nods, and steering wobbles to spot drowsiness before it
strikes.
● Timely wake-up calls: Chime-in alerts, seat vibrations, or even suggested rest stops keep you sharp and focused.

The benefits:

● Fewer crashes: Fewer sleepy drivers on the road means fewer accidents and a safer commute for everyone.
● Happier drivers: Stay alert, avoid accidents, and arrive at your destination refreshed and happy.

The IDM: Innovation for safer roads and happier drivers.

This shorter version emphasizes the key points, highlighting the problem, solution, and benefits, while keeping it concise
and engaging.
 INTRODUCTION

Falling asleep behind the wheel? Not anymore! Drowsy driving is a silent menace, causing thousands of
accidents yearly. Enter the Intelligent Drowsiness Monitor (IDM), your AI co-pilot for safer roads.

This project envisions a robust system that detects fatigue using a cocktail of sensors and smart algorithms. Eye
movements, erratic steering, even brainwaves – the IDM deciphers them all, spotting drowsiness before it strikes.
Timely alerts wake you up with chimes, vibrations, or even nudges towards rest stops.

Fewer crashes, happier commutes, and lives saved – that's the IDM promise. Join the fight against drowsy driving,
one blink at a time.

This shorter version condenses the key points into a punchier introduction, emphasizing the problem, solution,
and benefits, all within a concise and eye-catching format.

S.no Name of the paper
1. Real-Time Eye Blink
Detection and Tracking for
Driver Drowsiness
Monitoring System
2. Driver Drowsiness
Detection Using OpenCV
3. Drowsiness Detection
and Alert System for
Drivers Using OpenCV
4. Real-Time Detection of
Drowsiness Using
OpenCV
5. Driver Drowsiness Detection
System Based on Eye and
Mouth States Using OpenCV
Literature review
Published year - Journal Description
IEEE Transactions on This paper presents a real-time eye
Intelligent Transportation blink detection and tracking system
using OpenCV for monitoring driver
Systems(2018) drowsiness.
International Journal of This study proposes a driver
Computer Applications drowsiness detection system
(2016) based on facial feature analysis
using OpenCV.
Journal of Advanced The paper introduces a
Transportation(2019) drowsiness detection and alert
system for drivers utilizing
OpenCV for real-time facial
analysis.
Procedia Computer This paper presents a real-time
Science(2017) drowsiness detection method for
drivers employing OpenCV and
machine learning techniques.
IEEE Access(2020) The study proposes a driver
drowsiness detection system
utilizing OpenCV to analyze eye
and mouth states in real-time.
 Literature review
S.no Author Published year - Journal Description
6. Vision-Based Drowsiness IET Computer Vision(2015) This paper introduces a
Detection System for Drivers vision-based drowsiness detection
Using OpenCV system for drivers employing
OpenCV for facial feature extraction.

7. Real-Time Driver Journal of Advanced The study presents a real-time driver

Drowsiness Detection drowsiness detection system based on
Transportation(2018) OpenCV and Support Vector Machine
System Using OpenCV
(SVM) classification.
and SVM

8. Facial Feature-Based IEEE Access(2019) This paper proposes a facial

Drowsiness Detection feature-based drowsiness
System for Drivers Using detection system utilizing
OpenCV OpenCV for real-time analysis.

9. OpenCV-Based International Journal of The study presents an

Drowsiness Detection Advanced Computer Science OpenCV-based drowsiness
System for Drivers Using and Applications detection system for drivers
Facial Landmarks utilizing facial landmarks for
(2016) feature extraction.

10. Real-Time Eye State Journal of Information This paper introduces a real-time
Detection for Driver Processing Systems(2017) eye state detection method using
Drowsiness Monitoring OpenCV for driver drowsiness
Using OpenCV monitoring.

S.no Author
11. Driver Drowsiness Detection
System Using OpenCV and
Haar Cascade Classifiers
12. OpenCV-Based Drowsiness
Detection System for
Drivers Using Facial
Expression Analysis
13. Real-Time Driver
Drowsiness Detection
Using OpenCV and CNN
14. Facial Feature Extraction
for Driver Drowsiness
Detection System Using
OpenCV
15. Driver Drowsiness Detection
System Based on Eye Aspect
Ratio Using OpenCV
Literature review
Published year - Journal Description
International Journal of The study proposes a driver
Engineering and Advanced drowsiness detection system
Technology(2018) based on OpenCV and Haar
Cascade classifiers for facial
feature extraction.
International Journal of This paper presents an
Computer Science and OpenCV-based drowsiness
detection system for drivers
Information Security employing facial expression analysis
(2018) techniques.
Journal of Advanced The study introduces a real-time
Transportation(2019) driver drowsiness detection
method using OpenCV and
Convolutional Neural Networks
(CNN).
International Journal of This paper proposes a facial
Image, Graphics and Signal feature extraction method using
OpenCV for a driver drowsiness
Processing(2017) detection system.
International Journal of The study presents a driver
Computer Applications drowsiness detection system based on
eye aspect ratio analysis using
(2016) OpenCV for real-time monitoring.
 EXISTING SYSTEM

Here's a summary of existing drowsiness detection systems and their limitations:

● Camera-based systems: Track eye movements, but can be affected by lighting and glasses.
● Steering-based systems: Monitor steering patterns, but may not detect drowsiness
early enough.
● Physiological sensor systems: Measure heart rate or brain activity, but can be uncomfortable or sensitive
to external factors.
● Vehicle-based systems: Track lane departures or braking, but may not distinguish drowsiness from
other factors.
● Mobile app-based systems: Use smartphone sensors, but limited by battery life and accuracy.

The IDM aims to overcome these limitations with a multi-sensor approach, advanced algorithms, and
personalized interventions.
 Proposed System

Drowsy driving, a silent predator on the road, claims countless lives each year. To combat this threat, innovative

drowsiness detection systems emerge as digital copilots, vigilantly guarding against fatigue behind the wheel. These systems

don't merely react; they predict. Forget the red flags like closed eyes or slumped posture; these intelligent guardians can

decipher even the subtlest cues. A yawn held back through strained smiles, a fleeting head bob followed by frantic eye

widening – these tell-tale signs are all captured by the system's watchful "eye," a strategically placed camera. But unlike a

passive observer, the system employs deep learning algorithms, the same technology powering cutting-edge image

recognition. It isolates your face, analyzes your eyes, and interprets these nuances with remarkable accuracy. Think of it as

having a personal fatigue gauge on your dashboard, constantly assessing your alertness and sounding an alarm before

drowsiness truly takes hold. This early warning system can be the difference between a safe journey and a potentially

disastrous one. So, the next time you hit the road, picture this guardian by your side, ensuring every mile is driven with the

clarity and focus essential for reaching your destination safely.

Block Diagram
System code:
 Methodology

• Data Collection : Curated diverse dataset capturing varying levels of alertness and
drowsiness and annotations added to label different drowsiness states like open eyes, closed
eyes, and other facial cues.
• Preprocessing : Resized, normalized, and augmented data to enhance variability and prepare
for model training.
• Model Selection : Choose Convolutional Neural Network (CNN) architecture for its
effectiveness in image recognition tasks and Evaluated pre-trained models specialized in
facial recognition and expression analysis.
• Model Training : Split dataset into training, validation, and test sets and trained selected
model, optimized parameters, and fine-tuned hyperparameters based on validation set
performance.
• Integration with OpenCV : Utilized OpenCV for real-time video processing and facial
detection, ensuring seamless integration.
• Facial Landmark Detection : Used libraries like dlib for accurate facial landmark detection,
extracting features crucial for drowsiness detection.
• Drowsiness Detection Algorithm : Calculated Eye Aspect Ratio (EAR) and employed
advanced algorithms to analyze facial expressions for subtle cues indicative of drowsiness.
• Alert Mechanism : Integrated visual, auditory, or haptic alerts to promptly notify the driver
upon detecting signs of drowsiness.
 References

1.National Crime Records Bureau (NCRB), Ministry of Home Affairs, and Government of India. (Oct. 2021). Accidental Deaths and
Suicides in India. [Online]. Available: [Accidental Deaths and Suicides in India](
https://ncrb.gov.in/sites/default/files/ADSI_2020_FULL_REPORT.pdf)

2.World Health Organization. (2011). Mobile Phone Use: A Growing Problem of Driver Distraction. [Online]. Available: [Mobile Phone
Use: A Growing Problem of Driver
Distraction](https://www.who.int/violence_injury_prevention/publications/road_traffic/distracted_driving_en.pdf)

3.M. Ramzan, H. U. Khan, S. M. Awan, A. Ismail, M. Ilyas, and A. Mahmood, "A survey on state-of-the-art drowsiness detection
techniques," *IEEE Access*, vol. 7, pp. 61904–61919, 2019, doi: [10.1109/ACCESS.2019.2914373](
https://doi.org/10.1109/ACCESS.2019.2914373).

4.A. Dasgupta, D. Rahman, and A. Routray, "A smartphone-based drowsiness detection and warning system for automotive drivers,"
*IEEE Trans. Intell. Transp. Syst.*, vol. 20, no. 11, pp. 4045–4054, Nov. 2019, doi: [10.1109/TITS.2018.2879609](
https://doi.org/10.1109/TITS.2018.2879609).

5.C.-T. Lin, R.-C. Wu, S.-F. Liang, W.-H. Chao, Y.-J. Chen, and T.-P. Jung, "EEG-based drowsiness estimation for safety driving using
independent component analysis," *IEEE Trans. Circuits Syst. I, Reg. Papers*, vol. 52, no. 12, pp. 2726–2738, Dec. 2005, doi:
[10.1109/TCSI.2005.857555](https://doi.org/10.1109/TCSI.2005.857555).

6.Y.. Cui, Y. Xu, and D. Wu, "EEG-based driver drowsiness estimation using feature weighted episodic training," *IEEE Trans. Neural
Syst. Rehabil. Eng.*, vol. 27, no. 11, pp. 2263–2273, Nov. 2019, doi: [10.1109/TNSRE.2019.2945794](
https://doi.org/10.1109/TNSRE.2019.2945794).
 References
7. Y. Jiang, Y. Zhang, C. Lin, D. Wu, and C.-T. Lin, "EEG-based driver drowsiness estimation using an online
multi-view and transfer TSK fuzzy system," *IEEE Trans. Intell. Transp. Syst.*, vol. 22, no. 3, pp. 1752–1764, Mar. 2021,
doi: [10.1109/TITS.2020.2973673](https://doi.org/10.1109/TITS.2020.2973673).

8.W. Zhang, B. Cheng, and Y. Lin, "Driver drowsiness recognition based on computer vision technology," *Tsinghua Sci.
Technol.*, vol. 17, no. 3, pp. 354–362, Jun. 2012, doi: [10.1109/TST.2012.6216768](https://doi.org/10.1109/TST.2012.6216768).

9.M. A. Tanveer, M. J. Khan, M. J. Qureshi, N. Naseer, and K.-S. Hong, "Enhanced drowsiness detection using deep learning: An
fNIRS study," *IEEE Access*, vol. 7, pp. 137920–137929, 2019, doi: [10.1109/ACCESS.2019.2942838](
https://doi.org/10.1109/ACCESS.2019.2942838).

10.B.-G. Lee and W.-Y. Chung, "Driver alertness monitoring using fusion of facial features and bio-signals," *IEEE Sensors
J.*, vol. 12, no. 7, pp. 2416–2422, Jul. 2012, doi: [10.1109/JSEN.2012.2190505](https://doi.org/10.1109/JSEN.2012.2190505).

11.M. Kahlon and S. Ganesan, "Driver drowsiness detection system based on binary eyes image data," in *Proc. IEEE Int.
Conf. Electro/Inf. Technol. (EIT)*, May 2018, pp. 209–215, doi: [10.1109/EIT.2018.8500272](
https://doi.org/10.1109/EIT.2018.8500272).

12.M. H. Alkinani, W. Z. Khan, and Q. Arshad, "Detecting human driver inattentive and aggressive driving behavior using deep
learning: Recent advances, requirements and open challenges," *IEEE Access*, vol. 8, pp. 105008–105030, 2020, doi:
[10.1109/ACCESS.2020.2999829](https://doi.org/10.1109/ACCESS.2020.2999829).

13.C. Zhang, X. Wu, X. Zheng, and S. Yu, "Driver drowsiness detection using multi-channel second order blind
identifications," *IEEE Access*, vol. 7, pp. 11829–11843, 2019, doi: [10.1109/ACCESS.2019.2891971](
https://doi.org/10.1109/ACCESS.2019.2891971).
 References
14. U. Budak, V. Bajaj, Y. Akbulut, O. Atila, and A. Sengur, "An effective hybrid model for EEG-based drowsiness detection,"
*IEEE Sensors J.*, vol. 19, no. 17, pp. 7624–7631, Sep. 2019, doi:
[10.1109/JSEN.2019.2917850](https://doi.org/10.1109/JSEN.2019.2917850).

15.W. Deng and R. Wu, "Real-time driver-drowsiness detection system using facial features," *IEEE Access*, vol. 7, pp. 118727–
118738, 2019, doi: [10.1109/ACCESS.2019.2936663](https://doi.org/10.1109/ACCESS.2019.2936663).

16. M. Omidyeganeh, A. Javadtalab, and S

. Shirmohammadi, "Intelligent driver drowsiness detection through fusion of yawning and eye closure," in *Proc. IEEE Int. Conf. Virtual
Environ., Hum.-Comput. Interfaces Meas. Syst.*, Sep. 2011, pp. 1–6, doi: [10.1109/VECIMS.2011.6053857](
https://doi.org/10.1109/VECIMS.2011.6053857).