Download as pdf or txt
Download as pdf or txt
You are on page 1of 23

DRIVING ASSISTANCE

SYSTEM
PROJECT GUIDE: PRESENTED BY:
CHITHRA SHAJI THOMAS JAIN JAMES(MZW21CS009)
ASSISTANT PROFESSOR JOSH V GEORGE(MZW21CS012)
COMPUTER SCIENCE AND ENGINEERING NANDAKRISHNAN O(MZW21CS013)
MOUNT ZION INSTITUTE OF SCIENCE AND COMPUTER SCIENCE AND ENGINEERING
TECHNOLOGY,CHENGANNUR MOUNT ZION INSTITUTE OF SCIENCE
AND TECHNOLOGY,CHENGANNUR
INTRODUCTION
• Drowsiness is a state of near sleep, where the person has a strong desire for sleep. It has two
distinct meanings, referring both to the usual state preceding falling asleep and the chronic
condition referring to being in that state independent of a daily rhythm .
• Sleepiness can be dangerous when performing tasks that require constant concentration, such
as driving a vehicle. When a person is sufficiently fatigue while driving, they will experience
drowsiness and this leads to increase the factor of road accident.
• The development of technologies for detecting or preventing drowsiness while driving is a
majorchallenge in the field of accident avoidance system. Because of the hazard that
drowsinesspresents on the road, methods need to be developed for counteracting its affects.
• The aim of this project is to develop a simulation of drowsiness detection system. The focus
willbe placed on designing a system that will accurately monitor the open or closed state of
thedriver’s eyes and mouth.
• In this project we use a pre-trained model of image dection.
• This project is focused on the localization of the eyes and mouth, which involves looking at
the entire image of the face, and determining the position of the eyes and mouth, by
applying the existing methods in imageprocessing algorithm.

• This system also detect the accident too.
• When an accident is occurred it send an emergency message with the location of the vehicle to the conceded
authority
• The location sharing is possible on the basics of api of map
LITERATURE REVIEW
TITLE OF THE PROPOSED SYSTEM METHOD USED ADVANTAGES DISADVANTAGES
PROJECT

"Effectiveness of A:Integrating 1. Systematic 1.Increased awareness • Information


Emergency Alerts and multiple literature review to 2.Targeted messaging overload User
Public Warnings: A communication gather relevant 3.Real-time updates Acceptance
channels for
Systematic Literature research findings. • Privacy concerns
message
Review" dissemination.
2. Examination of • False alarms
Authors: Yin Leng B:Implementing a communication
Theng, Min Zhang, and standardized channels, message
Schubert Foo Published message format formats, and
in: International Journal for clarity and delivery
of Information consistency. mechanisms.
ManagementYear: 2019 C: Incorporating 3. Real-time
geolocation
monitoring and
technology for
targeted alerts to
updates for timely
specific areas. and accurate
D: Utilizing user information
feedback dissemination.
mechanisms to
assess message
effectiveness and
improve future
alerts.
TITLE OF THE PROPOSED SYSTEM METHOD USED ADVANTAGES DISADVANTAGES
PROJECT

Real-time drowsiness A: System targets 1.Eye Blink 1. Improved Road 1.Dependency on Eye
detection system using drowsy driving with Monitoring Safety Tracking
eye blink parameters. an eye blink Algorithm 2.Real-time Detection 2.False
monitoring
IEEE Sensors Journal, 2.Experimental 3.High Accuracy Positives/Negatives
algorithm.
16(20), 7368-7375. B: Algorithm
Evaluation 4.Non-intrusive 3.Limited Scope
(2016). assesses eye 3.Literature Survey 5.Cost-effective 4.User Acceptance
Authors: Karthikeyan, feature points to 5.Maintenance
N., Subramanian, K., detect open or andUpdates
Ravi, S., & closed eyes for
Murugappan, M. drowsiness.
C: Triggers an
alarm when
drowsiness is
detected to avert
accidents.
D: Achieves 94%
accuracy in
detecting
drowsiness,
showing potential
for real- time
application.
TITLE OF THE PROPOSED SYSTEM METHOD USED ADVANTAGES DISADVANTAGES
PROJECT

Google Maps API: Map 1.HTTP Requests 1. Easy Integration 1. Cost


Powerful Location- Display 2.RESTful APIs 2. Rich Features 2. Dependency
Based Services for the 3.Vector Graphics 3. Customization 3. Privacy Concerns
Web" Proceedings of the Geocod 4.Client-side 4. Cross-Platform 4.Complexity
16th International World ing Rendering Compatibility
Wide Web Conference
(WWW '07) Year: 2007 Street
Authors: Grant Miller, View
Chris Broadfoot, Bret
Taylor Traffic
Inform
ation
TITLE OF THE PROPOSED SYSTEM METHOD USED ADVANTAGES DISADVANTAGES
PROJECT

Jain, “Face Detection A: Innovative face 1.Skin Region 1. Robustness 1.Computational


In Color Images; detection in color Detection 2. Accuracy Complexity
international journal of images under various 2.Lighting 3. Versatility 2.Sensitivity to
conditions.
crowd science Compensation 4. Innovation Parameters
B: Employs lighting
Year:2017 compensation and
3.Nonlinear Color 3.Limited
Authors: R. L. Hsu, M. color Transformation Performance in
Abdelmottaleb, And A. transformation for 4.Spatial Arrangement Extreme
K. Jain skin identification. Analysis Conditions
C: Generates face 4.Resource Intensive
candidates from
spatially arranged
skin regions.
D: Maps facial
features to confirm
face candidates.
E: Aims for robust
detection across
diverse facial
variations,
proven by
experiments.
OBJECTIVES
• The primary objective is to establish a real-time system that closely monitors the driver's eyes, distinguishing
between fully open and closed states. This monitoring is crucial for detecting driver fatigue early and
preventing accidents.

• Fatigue detection involves analyzing eye movements and blinking patterns, particularly in a series of facial
images captured in live video.

• The ultimate aim is to create a real-time monitoring system that continuously tracks the driver's eye state,
whether they are fully open, closed, or somewhere in between, thereby ensuring timely intervention to prevent
accidents.

• By alerting the driver when they are drowsy or fatigued, the system helps prevent accidents caused by
impaired driving. By intervening before a potential accident occurs, it contributes to overall road safety.

• In addition to alerting the driver, the system also notifies relevant authorities about the accident's occurrence
and the vehicle's location. This feature enables swift emergency response and assistance, potentially saving
lives and minimizing the severity of injuries.

• Additionally, the system is designed to provide a call to the relevant authorities for easy notification and
verification of messages, enabling them to take necessary actions promptly in response to potential accidents
or emergencies.
PROPOSED SYSTEM
• Face recognition technology is integrated into the system to detect the unconsciousness of the driver. This
feature aids in identifying fatigue, which is a precursor to sleepiness.

• By leveraging face recognition, the system can detect signs of fatigue in the driver. Since fatigue precedes
sleepiness, detecting it early allows for timely alerts to awaken the driver and reduce the risk of accidents.

• The system primarily relies on detecting highlights of the eyes, typically reflections, within the video image
of the driver. This technique is utilized to locate the eyes on the face and identify instances where they are
closed.

• Initially, the project aimed to use retinal reflection as a means to locate the eyes and identify closures. The
absence of this reflection indicates closed eyes. Analyzing sequential video frames facilitates the calculation
of eye closure duration.

• Eye closure duration for drowsy drivers tends to be longer than normal blinking intervals. Even a slightly
longer closure duration can significantly increase the risk of a severe crash. Therefore, immediate alerts are
triggered upon detecting closed eyes.

• Additionally, the system includes an accident detection and emergency alert feature. In the event of an
accident, it automatically sends an emergency alert message along with the vehicle's location to the nearest
emergency centers for swift assistance also send a call.
ARCHITECTURE
ARCHITECTURE OF DROWSINESS DECTION
INPUT PREPROCESSING OBJECT
DECTION(YOLOV5)

EYE STATE
CLASSIFICATION EYE DECTECTION FACE DETECTION

DROWSINESS DECTION OUTPUT


ARCHITECTURE OF ACCIDENT REPORT
MESSAGE SENDING
ACCIDENT DETECTION LOCATION TRACKING
MODULE
MODULE MODULE

AUTHORITY
CONCERNED CALL SENDING
IDENTIFICATION
AUTHORITIES MODULE
MODULE
CONCLUSION
• The driver assistance system represents a significant advancement in leveraging technology to enhance road
safety.

• Through the integration of face recognition and eye tracking technologies, the system can effectively detect
early signs of driver fatigue and unconsciousness.

• Prompt alerts are issued to drivers upon detection of fatigue or unconsciousness, enabling timely interventions
to prevent accidents.

• The system's reliance on eye highlights and the development of an algorithm for eye closure detection ensure
precise monitoring of driver alertness levels in real-time.

• The inclusion of an accident detection and emergency alert system facilitates rapid communication of critical
information to relevant authorities and emergency response teams.

• By proactively addressing the risks associated with driver fatigue, the project aims to significantly reduce the
occurrence of accidents and improve overall road safety.

• As technology continues to evolve, there is potential for further refinement and deployment of the system to
make meaningful contributions towards safer transportation systems globally.
REFERENCES
[1] Authors: Yin Leng Theng, Min Zhang, and Schubert Foo "Effectiveness of Emergency Alerts and
Public Warnings: A Systematic Literature Review" Published in: International Journal of
Information ManagementYear: 2019.
[2] R. L. Hsu, M. Abdelmottaleb, And A. K. Jain, “Face Detection In Color Images;,international journal of crowd
science Year:2017.
[3] Karthikeyan, N., Subramanian, K., Ravi, S., & Murugappan, M. (2016). Real-time drowsiness detection
system using eye blink parameters. IEEE Sensors Journal, 16(20), 7368-7375.
[4] Authors: Grant Miller, Chris Broadfoot, Bret Taylor “Google Maps API: Powerful Location-Based Services
for the Web" Published in: Proceedings of the 16th International World Wide Web Conference (WWW '07) Year:
2007.
THANK YOU

You might also like