VISVESVARAYA TECHNOLOGICAL UNIVERSITY

BELAGAVI

A Synopsis on
“Driver Drowsiness Detection and Alerting”
Submitted in partial fulfillment of the requirement for the award of
degree of
MASTER OF COMPUTER APPLICATIONS
Submitted by
JAYANTH C L 4JN22MC024
M SUBRAMANYA 4JN22MC032

Department of Master of Computer Applications,

J N N College of Engineering
Navule, Savalanga Road, Shivamogga, Karnataka 577204
2023
 VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI

A Synopsis on
“Driver Drowsiness Detection and Alerting”
Submitted in partial fulfillment of the requirement for the award of
degree of
MASTER OF COMPUTER APPLICATIONS
Submitted by
JAYANTH C L 4JN22MC024
M SUBRAMANYA 4JN22MC032
during the academic year 2023-2024
under the guidance of
Internal Guide Director
______________ ______________
Mr. Sampath Kumar S Dr. Prabhudeva S
Assistant Professor Professor
Dept. of MCA Dept. of MCA
Department of Master of Computer Applications,
J N N College of Engineering
Navule, Savalanga Road, Shivamogga, Karnataka 577204,
2023
Driver Drowsiness Detection and Alerting JNNCE

ABSTRACT:

The increasing number of road accidents attributed to driver drowsiness poses a significant threat
to road safety. In response to this challenge, this research proposes a Driver Drowsiness
Detection and Alerting System (DDDAS) designed to mitigate the risks associated with fatigued
driving. The system utilizes advanced computer vision and machine learning techniques to
monitor driver behaviour and accurately identify signs of drowsiness.

The proposed system employs a combination of facial recognition, eye tracking, and other
physiological indicators to assess the driver's alertness level. A camera installed within the
vehicle captures real-time images of the driver's face and monitors key features such as eye
closure, head movements, and facial expressions. These data are then processed using deep
learning algorithms to detect patterns indicative of drowsiness.

INTRODUCTION:

The modern era's reliance on vehicular transportation has brought with it a concerning rise in
road accidents attributed to driver drowsiness. As individuals spend extended periods behind the
wheel, fatigue-induced impairment becomes a pervasive issue, posing a severe threat to road
safety. Recognizing the imperative to address this challenge, there is a pressing need for
innovative solutions that go beyond conventional methods. Current approaches to driver
drowsiness detection often lack the real-time precision required to intervene effectively, leading
to a critical gap in ensuring timely alerts. This introduces a compelling opportunity to develop an
advanced system that utilizes state-of-the-art technologies, such as computer vision and machine
learning, to not only detect signs of driver drowsiness but also deliver immediate and accurate
alerts. By exploring this avenue, we aim to significantly enhance road safety, minimize the risks
associated with drowsy driving, and ultimately save lives on our roadways.

Department of MCA 3|Page

Driver Drowsiness Detection and Alerting JNNCE

PROJECT OBJECTIVES:

Enhance Driver Safety: The main goal of the project is to significantly enhance driver safety by
detecting and addressing instances of drowsiness and distracted driving in real-time. This will
help reduce the number of accidents caused by these factors.

Accurate Drowsiness Detection: Develop an accurate and reliable drowsiness detection system
by leveraging facial landmark detection and yawning analysis. The system should be capable of
identifying even subtle signs of driver fatigue.

Real-time Detection: Develop a robust real-time system capable of accurately detecting signs of
driver drowsiness through the analysis of various indicators, including facial expressions, eye
movements, and physiological parameters.

EXISTING SYSTEM:

Currently, there are existing systems which detect drowsiness based on physical cues or
physiological cues separately. For instance, an attempt was made to study the pressure of a
driver’s hand on the steering wheel in order to detect fatigue.

Detecting of fatigue states of a car driver likely discuss methods and techniques for detecting
fatigue states in car drivers. Detection of driver drowsiness using wavelet analysis of eye blink
and a support vector machine classifier is likely to focus on the utilization of wavelet analysis
and support vector machines to identify drowsiness in drivers based on eye blink patterns.
Robust real-time face detection, possibly discussing techniques for real-time face detection,
which may have applications in driver monitoring systems. Faces as releasers of contagious
yawning, An approach to face detection using normal human subjects might explore how facial
expressions, particularly yawning, can be indicators of certain states, possibly related to fatigue.
Driver behavior analysis for safe driving likely provides an overview of various approaches and
technologies used for analyzing driver behavior to enhance safety.

Department of MCA 4|Page

Driver Drowsiness Detection and Alerting JNNCE

PROPOSED SYSTEM:

The proposed system is cost effective, easy to implement and reliable compared to the existing
system. The system doesn’t utilize sensors because the sensor’s value may vary depending upon
the change in temperature and humidity, so we have utilized a webcam so that the parameters
don’t vary with changes in temperature and humidity, by using a webcam the complexity of the
system will be reduced and the code runs very efficiently.

The system uses just a webcam and a laptop in order to detect the driver’s drowsiness and alerts
the user if he/she is getting tired through visually and audibly.

SCOPE OF THE PROJECT:

The scope of this project is to develop a comprehensive and intelligent driver safety
enhancement system that utilizes computer vision and machine learning techniques to address
two critical aspects of road safety: driver drowsiness detection and distracted driving
identification.

CONCLUSION:

The development of an advanced driver drowsiness detection and alerting system represents a
crucial step towards addressing the pervasive issue of road accidents caused by driver fatigue.
Through the integration of cutting-edge technologies, such as computer vision, machine learning,
and advanced sensors, this project strives to create a comprehensive and real-time solution. By
focusing on customizable alerting mechanisms and seamless integration with vehicle systems,
our aim is to not only accurately identify signs of drowsiness but also provide timely and
appropriate alerts to prevent potential accidents. The potential impact of this system on road
safety is substantial, with the ability to save lives, minimize injuries, and contribute to a safer and
more secure transportation environment. As we navigate the future of automotive technology,
this project serves as a testament to the commitment to innovative solutions that prioritize the
well-being of drivers and passengers alike.

REFERENCES:

Department of MCA 5|Page

Driver Drowsiness Detection and Alerting JNNCE
[1] Bittner, Roman, et al. “Detecting of fatigue states of a car driver.” Springer Berlin
Heidelberg, 2014. 260-273.

[2] Li, Gang, and Wan-Young Chung. “Detection of driver drowsiness using wavelet analysis of
eye blink and a support vector machine classifier.” Sensors 13.12 (2016): 16494-16511.

[3] Viola, Paul, and Michael J. Jones. “Robust real-time face detection.” International journal of
computer vision 57.2 (2017): 137-154.

[4] Provine, Robert R. “Faces as releasers of contagious yawning: An approach to face detection
using normal human subjects.” Bulletin of the Psychonomic Society 27.3 (2015): 211-214.

[5] S. Kaplan, M. A. Guvensan, A. G. Yavuz, and Y. Karalurt, “Driver behavior analysis for safe
driving: A survey,” IEEE Trans. Intell. Transp. Syst., vol. 16, no. 6, pp. 3017–3032, Dec. 2015.
Certainly! Here are additional references related to driver fatigue detection, driver behavior
analysis, and related topics:

[6] Feng, D. D., Wang, J., & McManis, B. (2015). Driver fatigue and drowsiness monitoring
system with embedded electrocardiogram sensor on steering wheel. IEEE Transactions on
Biomedical Engineering, 62(7), 1748-1757.

[7] Ohn-Bar, E., & Trivedi, M. M. (2014). Looking at humans in the age of self-driving and
highly automated vehicles. IEEE Transactions on Intelligent Transportation Systems, 16(4),
2335-2345.

[8] Xu, X., Chen, F., Sun, J., & Zhang, Y. (2017). Real-time driver fatigue detection based on eye
tracking and dynamic Bayesian network. Transportation Research Part C: Emerging
Technologies, 82, 52-68.

[9] Hong, Y., & Peng, Y. (2018). Driver drowsiness detection using EEG and genetic algorithm.
IEEE Transactions on Intelligent Transportation Systems, 19(3), 963-972.

Department of MCA 6|Page