DRIVER DROWSINESS DETECTION SYSTEM

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 10 Issue: 11 | Nov 2023 www.irjet.net p-ISSN: 2395-0072
DRIVER DROWSINESS DETECTION SYSTEM
B. Jagadeesh1,A. Umesh Chandra2,G. Uday Sankar Reddy3, G. Satish4, Md. Shakeel Ahmed5
1,2,3,4 Department of Information Technology, VVIT, AP, India
5Associate Professor, Dept. of Information Technology, VVIT, AP,India
-----------------------------------------------------------------------***-----------------------------------------------------------------------
Abstract - The proposed system is an intelligent driver
drowsiness and distraction detection system designed to
enhance road safety. By utilizing computer vision
techniques and facial landmarks analysis, the system aims
to monitor the driver's eye and mouth activities in real-
time. It triggers alarms and alerts the driver when signs of
drowsiness or distraction are detected. The system
contributes to reducing the risk of accidents caused by
driver fatigue and inattention
Key Words: OpenCV, Dlib, Face Recognition, Computer
Vision (CV), Drowsiness Detection.
1.INTRODUCTION
2.EXISTING SYSTEM
The existing system utilizes libraries such as scipy,
imutils, pygame, dlib, and cv2 to build a real-time driver
drowsiness detection system. It processes video frames
from a webcam, detects facial landmarks, calculates the
eye aspect ratio and triggers alarms when the driver is
detected to be drowsy. The system includes features to
handle different levels of drowsiness and distraction
scenarios.
Some of the major disadvantages includes:
(1) The existing system focuses solely on drowsiness
detection, not distraction detection.
(2) It lacks a comprehensive approach to handling different
types of distractions.
(3) The system might generate false alarms or fail to detect
certain scenarios due to limited feature coverage.
(4) The system might generate false alarms or fail to detect
certain scenarios due to limited feature coverage.
3.PROPOSED SYSTEM
The proposed system enhances the capabilities of the
existing system by introducing distraction detection in
addition to drowsiness detection. It utilizes dlib for face and
landmark detection, and calculates the eye and mouth
aspect ratios. The system maintains different timers for
drowsiness and distraction detection intervals. Alarms are
triggered based on predefined thresholds and intervals.
Additionally, it provides feedback on the level of drowsiness
or distraction detected, offering a more comprehensive
solution.
The project initiates by setting up the video capture
interface with the webcam using OpenCV, a widely used
open-source computer vision library. The
cv2.VideoCapture(0) function initializes a video capture
object to access the camera, enabling the system to read
video data from this object for subsequent processing.
Driver fatigue and distractions are major contributors to
road accidents. To enhance road safety, the proposed
system employs computer vision and facial landmarks
analysis. By monitoring eye and mouth movements in real
time, it detects drowsiness and distractions that can
impair driving.
The system's use of advanced algorithms and libraries
enables accurate evaluation of the driver's state. Key
metrics like eye aspect ratio (EAR) and mouth aspect ratio
(MAR) provide vital insights. Alarms and alerts are
triggered when these metrics deviate from safe levels,
prompting timely corrective action. This system's
proactive approach shows potential in reducing accidents
causedby fatigueand distractions, thus making roads safer
for everyone
Fig : Block Diagram of Proposed System
© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008Certified Journal | Page 124

p-ISSN: 2395-0072
Volume: 10 Issue: 10 | Oct 2023 www.irjet.net
OBJECTIVES
(1) Real-time detection of driver drowsiness and
distraction using facial landmarks.
(2) Utilizing eye aspect ratios (EAR) and mouth aspect
ratios (MAR) for drowsiness and distraction
identification.
(3) Implementing sound alarms to alert the driver
in case of drowsiness or distraction.
(4) Integrating computer vision techniques for accurate
facial feature extraction and analysis
(5) Providing a user-friendly interface with live video feed
for monitoring.
(6) Enabling automatic detectionand alertingwithout the
need for any external hardware.
5.METHODOLOGY
The methodology implemented in the system is divided
into four modules as follows:
1. Face Recognition
2. Detection of Drowsiness
3. Detection of Distraction
4. User Interface and Interaction
By implementing these four modules step by step Driver
Drowsiness Detection System is developed. In this
proposed framework, weare going to utilize camera and the
speaker for the reading inputs and playing outputs.
This module focuses on accurately detecting and
interpreting user hand gestures. Utilizes computer vision
libraries such as OpenCV for real-time video capturing.
5.2. DETECTION OF DROWSINESS
This module will identify whether the driver is drowsy or
not after detecting the face it analyzes the face which was
captured through webcam based on eye and mouth
movements of the driver. We have used Dlib library for
identifying facial landmarks.
4.
Moving forward, the system leverages the dlib and imutils
libraries for facial processing. The
dlib.get_frontal_face_detector () function detects the
presence of frontal faces in the video frames, while the
dlib.shape_predictor(shape_predictor_path) function
identifies the specific facial landmarks necessary for
calculating the eye and mouth aspect ratios.
The code continuously captures frames from the video
feed, processes them, and displays the frames in a window
using OpenCV's cv2.imshow() function. Various
computed parameters, such as the eye aspect ratio (EAR),
mouth aspect ratio (MAR), and the frames-per-second
(FPS), are displayed on the screen to provide real-time
feedback to the user. Additionally, the system triggers
audio alerts using the Pygame mixer library when
drowsiness, yawning, or distraction is detected based on
the computed facial parameters and predefined
thresholds.
The user can exit the application by pressing the 'q' key.
The proposed system integrates multiple components,
including facial landmark detection, aspect ratio
calculations, and real-time audiovisual feedback, to create
an effective driver drowsiness and distraction detection
mechanism using computer vision techniques.
5.1. FACE RECOGNITION
© 2023, IRJET | ImpactFactor value: 8.226 | ISO 9001:2008Certified Journal | Page 125

p-ISSN: 2395-0072
5.3. DETECTION OF DISTRACTION
5.4 USER INTERFACE AND INTERACTION
6.OUTPUT SNAPSHOTS
Ensures a user-friendly and intuitive interaction experience
by providing audio feedback. Includes a graphical user
interface for user guidance and interaction management.
This module will identify whether the user is distracted or
not after detecting the face through webcam it analyzes the
video and checks whether the driver is seeing the road or
not.
7.CONCLUSION
This real-time facial monitoring system is a significant step
toward making various activities safer, such as driving and
healthcare.
It's easy to customize and has the potential for more
improvements, like connecting to the internet or
understanding changes in how people talk.
This system leverages computer vision techniques and facial
landmark detection to address the critical issues of
drowsiness and distraction in individuals, alerting them
promptly to mitigate potential risks.

p-ISSN: 2395-0072
8.FUTURE ENHANCEMENT
(1) Adaptive Alarms: Customize alarm responses based on
the severity of drowsiness or distraction. For instance, the
system can issue a gentle alert for mild drowsiness and a
more urgent warning for extreme cases.
(2) Multi-Modal Sensing: Integrate additional sensors, such
as heart rate monitors or EEG sensors, to complement facial
monitoring. Combining multiple sources of data can enhance
the system's accuracy and reliability in detecting drowsiness
and distraction.
(3) Integration with Wearables: Extend the system's
functionality to wearables, such as smart glasses or
augmented reality (AR) headsets. Users can benefit from
real-time alerts displayed in their field of vision.
(4) Alert Preferences: Allow users to customize their alert
preferences, including the choice of alarms, alarm volume,
and visual cues. Personalized settings can make the system
more user-friendly.
9.REFERENCES
1]. Ameratunga.S, Bailey.J, Connor.J, Civil.I, Dunn.R,
Jackson.R, Norton.R, and Robinson.E, ―Driver sleepiness and
risk of serious injury to car occupants: Population control
study. ‖ British Medical Journal, vol. 324, 2002, pp. 1125–
1129.
[2]. Bronte.S, Bergasa.L, Delgado.B, Garcia.I, Hernandez.N
and Sevillano.M, ―Vision- based drowsiness detector for a
realistic driving simulator, ‖ in IEEE Intelligent
Transportations Systems Conference (ITSC), 2010.
[3]. Distante. A, D’Orazio. T, Guaragnella. C and Leo .M, ―A
visual approach for driver inattention detection,
‖Pattern Recogn., vol.40, no. 8, 2007, pp. 2341–2355.
[4]. Bradski. G, Kaehler. A, -Learning OpenCV, O’Reilly, 2008.
[5]. Igarashi.K, Itou.K, Itakura.F, Miyajima.C, Ozawa.T,
Takeda.K and Wakita.T, ―Driver identification using
driving behavior signals, ‖ IEICE - Trans. Inf. Syst., vol. E89-
D, 2006.
individual differences. ‖ Systems, Man
[6]. Nakano.T, Suzuki.M, Yamamoto.N, Yamamoto.O
and Yamamoto.S, ―Measurement of driver’s
consciousness by image processing a method for
presuming driver’s drowsiness by eye-blinks coping
with

DRIVER DROWSINESS DETECTION SYSTEM

More Related Content

Similar to DRIVER DROWSINESS DETECTION SYSTEM (20)

More from IRJET Journal (20)

Recently uploaded (20)

DRIVER DROWSINESS DETECTION SYSTEM