DRIVER DROWSINESS
DETECTION
Abstract
This system will monitor
the driver eyes and mouth
using a camera and we can
detect symptoms of driver
fatigue early enough to
avoid the person falling
from sleeping. So, this
project will be helpful in
detecting driver fatigue in
advance and will give
warning output.
different statistics were reported about accidents that happened due to driver fatigue and distraction. Generally,
the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of
concentration.
Introduction
Different statistics were reported about accidents that happened due to driver
fatigue and distraction. Generally, the main reason of about 20% of the crashes
and 30% of fatal crashes is the driver drowsiness and lack of concentration.
The driver face monitoring system is a real-time system that investigates the
driver physical condition based on the processing of driver face images. The
driver state can be estimated from the eye closure, eyelid distance, blinking,
yawning
different statistics were reported about accidents that happened due to driver fatigue and distraction. Generally,
the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of
concentration.
Proposed System
We measure physical changes (i.e. open/closed eyes and open/close mouth) is
well suited for real world conditions since it is non-intrusive by using a video
camera to detect changes.
In addition, micro sleeps that are short period of sleeps lasting 2 to 3 minutes are
good indicators of fatigue. Thus, by continuously monitoring the eyes of the
driver one can detect the sleepy state of driver and a timely warning is issued.
different statistics were reported about accidents that happened due to driver fatigue and distraction. Generally,
the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of
concentration.
Algorithem Used
Model Used : CascadeClassifier
This model detects the faces of an individual but unable to track
the eye closing/opening and mouth closing/opening moments so we have
decided to use Face landmark detection Model inorder to keep track ok
the moments of eye and mouth
Model used : Face landmark detection
Library used : Dlib
Algorithm used : CNN
different statistics were reported about accidents that happened due to driver fatigue and distraction. Generally,
the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of
concentration.
System Architecture
Model used : Face landmark detection
Library used : Dlib
Algorithm used : CNN
Face landmark detection is trained on the
iBUG-300 W dataset, where it contains images
and their corresponding 68 face landmark
points. In general, those landmark points belong
to the nose, the eyes, the mouth, and the edge
of a face.
DLib face detection uses histogram oriented
methods(HOG) and landmark detection is
based on Kazemi’s model . It returns different
68 feature points from a face.
different statistics were reported about accidents that happened due to driver fatigue and distraction. Generally,
the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of
concentration.
System Architecture
different statistics were reported about accidents that happened due to driver fatigue and distraction. Generally,
the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of
concentration.
Software Requirements
OS : Windows
Python : 3.10
different statistics were reported about accidents that happened due to driver fatigue and distraction. Generally,
the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of
concentration.
Hardware Requirements
Processor : core i3 minimun
RAM : 4GB (min)
Hard Disk : 500GB (min)
Input : Video Streaming
different statistics were reported about accidents that happened due to driver fatigue and distraction. Generally,
the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of
concentration.
Conclusion
During the monitoring, the system is able to decide whether the eyes are opened or
closed and mouth opened or closed. When the eyes have been closed and mouth is
opened, a warning signal is issued.This System achieves highly accurate and reliable
detection of drowsiness.
It offers a non-intrusive approach to detect drowsiness without the annoyance and
interference. Processing, judges the driver’s alertness level on the basis of continuous eye
closures. The proposed system works in both day time and night time conditions.
different statistics were reported about accidents that happened due to driver fatigue and distraction. Generally,
the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of
concentration.
References
T.Ahonen,A.Hadid and M.Pietikainen “phase description with local binary patterns:
application to face recognition” IEEE Trans. pattern Anal. March
Intell.,vol.28,no.12,pp.2037- 2041,Dec 2006.
Association for Safe International Road Travel ( ASIRT), Road Crash Statistics.
http://asirt.org/initiatives/ informing-road-users/road-safety-facts/road-crash statistics,
2016.
Drowsy Driving, Facts and Stats: Drowsy Driving – Stay Alert, Arrive Alive.
http://drowsydriving.org/about/facts- and- stats/ , 2016.
S. Hu and G. Zheng, “Driver drowsiness detection with eyelid related parameters by
Support Vector Machine,” International Journal of Expert Systems with Applications,
vol. 36, 2009, pp. 7651–7658, doi: http://dx.doi.org/10.1016/j.eswa.2008.09.030.
THANK YOU

ppt_Drowsin ess.pptx

  • 1.
  • 2.
    Abstract This system willmonitor the driver eyes and mouth using a camera and we can detect symptoms of driver fatigue early enough to avoid the person falling from sleeping. So, this project will be helpful in detecting driver fatigue in advance and will give warning output.
  • 3.
    different statistics werereported about accidents that happened due to driver fatigue and distraction. Generally, the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of concentration. Introduction Different statistics were reported about accidents that happened due to driver fatigue and distraction. Generally, the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of concentration. The driver face monitoring system is a real-time system that investigates the driver physical condition based on the processing of driver face images. The driver state can be estimated from the eye closure, eyelid distance, blinking, yawning
  • 4.
    different statistics werereported about accidents that happened due to driver fatigue and distraction. Generally, the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of concentration. Proposed System We measure physical changes (i.e. open/closed eyes and open/close mouth) is well suited for real world conditions since it is non-intrusive by using a video camera to detect changes. In addition, micro sleeps that are short period of sleeps lasting 2 to 3 minutes are good indicators of fatigue. Thus, by continuously monitoring the eyes of the driver one can detect the sleepy state of driver and a timely warning is issued.
  • 5.
    different statistics werereported about accidents that happened due to driver fatigue and distraction. Generally, the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of concentration. Algorithem Used Model Used : CascadeClassifier This model detects the faces of an individual but unable to track the eye closing/opening and mouth closing/opening moments so we have decided to use Face landmark detection Model inorder to keep track ok the moments of eye and mouth Model used : Face landmark detection Library used : Dlib Algorithm used : CNN
  • 6.
    different statistics werereported about accidents that happened due to driver fatigue and distraction. Generally, the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of concentration. System Architecture Model used : Face landmark detection Library used : Dlib Algorithm used : CNN Face landmark detection is trained on the iBUG-300 W dataset, where it contains images and their corresponding 68 face landmark points. In general, those landmark points belong to the nose, the eyes, the mouth, and the edge of a face. DLib face detection uses histogram oriented methods(HOG) and landmark detection is based on Kazemi’s model . It returns different 68 feature points from a face.
  • 7.
    different statistics werereported about accidents that happened due to driver fatigue and distraction. Generally, the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of concentration. System Architecture
  • 8.
    different statistics werereported about accidents that happened due to driver fatigue and distraction. Generally, the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of concentration. Software Requirements OS : Windows Python : 3.10
  • 9.
    different statistics werereported about accidents that happened due to driver fatigue and distraction. Generally, the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of concentration. Hardware Requirements Processor : core i3 minimun RAM : 4GB (min) Hard Disk : 500GB (min) Input : Video Streaming
  • 10.
    different statistics werereported about accidents that happened due to driver fatigue and distraction. Generally, the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of concentration. Conclusion During the monitoring, the system is able to decide whether the eyes are opened or closed and mouth opened or closed. When the eyes have been closed and mouth is opened, a warning signal is issued.This System achieves highly accurate and reliable detection of drowsiness. It offers a non-intrusive approach to detect drowsiness without the annoyance and interference. Processing, judges the driver’s alertness level on the basis of continuous eye closures. The proposed system works in both day time and night time conditions.
  • 11.
    different statistics werereported about accidents that happened due to driver fatigue and distraction. Generally, the main reason of about 20% of the crashes and 30% of fatal crashes is the driver drowsiness and lack of concentration. References T.Ahonen,A.Hadid and M.Pietikainen “phase description with local binary patterns: application to face recognition” IEEE Trans. pattern Anal. March Intell.,vol.28,no.12,pp.2037- 2041,Dec 2006. Association for Safe International Road Travel ( ASIRT), Road Crash Statistics. http://asirt.org/initiatives/ informing-road-users/road-safety-facts/road-crash statistics, 2016. Drowsy Driving, Facts and Stats: Drowsy Driving – Stay Alert, Arrive Alive. http://drowsydriving.org/about/facts- and- stats/ , 2016. S. Hu and G. Zheng, “Driver drowsiness detection with eyelid related parameters by Support Vector Machine,” International Journal of Expert Systems with Applications, vol. 36, 2009, pp. 7651–7658, doi: http://dx.doi.org/10.1016/j.eswa.2008.09.030.
  • 12.