DROWSINESS

1. DROWSINESS DETECTION USING OPENCV
AND MACHINE LEARNING
Project Supervisor : Mr.,.,
Team Member : 1.
Reg.No. XXXXX
2.
Reg.No. xxxxxxx

2. Introduction
• In recent years, an increase in the demand for modern transportation necessitates a faster car-parc growth. At present,
the automobile is an essential mode of transportation for people. Although the automobile has changed people’s lifestyle
and improved the convenience of conducting daily activities, it is also associated with numerous negative effects, such as
traffic accidents.
• fatigued driving is a significant and latent danger in traffic accidents. In recent years, the fatigue-driving-detection system
has become a hot research topic.
• The detection methods are categorized as subjective and objective detection. In the subjective detection method, a driver
must participate in the evaluation, which is associated with the driver’s subjective perceptions through steps such as self-
questioning, The associate editor coordinating the review of this article and approving it for publication was Gustavo
Olague. evaluation and filling in questionnaires. Then, these data are used to estimate the vehicles being driven by tired
drivers, assisting the drivers to plan their schedules accordingly. However, drivers’ feedback is not required in the objective
detection method as it monitors the driver’s physiological state and driving-behavior characteristics in real time.
• The collected data are used to evaluate the driver’s level of fatigue. Furthermore, objective detection is categorized into
two: contact and non-contact. Compared with the contact method, non-contact is cheaper and more convenient because
the system that not require Computer Vision technology or sophisticate camera allow the use of the device in more cars.
Owing to easy installation and low cost, the non-contact method has been widely used for fatigue-driving detection.
• For instance, Attention Technologies and SmartEye employ the movement of the driver’s eyes and position of the driver’s
head to determine the level of their fatigue. In this study, we propose a non-contact method to detect the level of the
driver’s fatigue. Our method employs the use of only the vehicle-mounted camera, making it unnecessary for the driver to
carry any on/in-body devices. Our design uses each frame image to analyze and detect the driver’s state

3. Objective
• Driver drowsiness detection is a car safety technology which helps to save the life
of the driver by preventing accidents when the driver is getting drowsy.
• The main objective is to first design a system to detect driver’s drowsiness by
continuously monitoring retina of the eye.
• The system works in spite of driver wearing spectacles and in various lighting
conditions.
• To alert the driver on the detection of drowsiness by using buzzer or alarm.
• Speed of the vehicle can be reduced.
• Traffic management can be maintained by reducing the accidents

4. ABSTARCT:
• The face, an important part of the body, conveys a lot of information. When a
driver is in a state of fatigue, the facial expressions, e.g., the frequency of blinking
and yawning, are different from those in the normal state.
• In this project, we propose a system, which detects the drivers' fatigue status,
such as yawning, blinking, and duration of eye closure, using video images,
without equipping their bodies with devices.
• In this study, we propose a computer vision based method to detect driver’s
drowsiness from a video taken by a camera. The method attempts to recognize
the face and then detecting the eye in every frame.
• Further, we designed a new detection method for facial regions based on 68 key
points. Then we use these facial regions to evaluate the drivers' state.
• By combining the features of the eyes and mouth, we can alert the driver using a
fatigue warning with the alarm sound.

5. EXISTING SYSTEM:
• The paper's motive is to demonstrate the implementation of a driver’s
drowsiness detection using MATLAB through image processing. Studies suggest
that about one-fourth of all serious road accidents occur because of the vehicle
drivers' drowsiness where they need to take, confirming that drowsiness gives
rise to more road accidents than accidents occur through Drink and Drive.
• Drowsiness Detection System is designed by employing vision-based concepts.
The system’s main component is a small camera pointing towards the driver's
face scan and monitoring the driver's eyes to detect drowsiness
• There are various methods like detecting objects which are near to vehicle and
front and rear cameras for detecting vehicles approaching near to vehicle and
airbag system which can save lives after an accident is accorded.

6. PROBLEM STATEMENT
• Fatigue is a safety problem that has not yet been deeply tackled by any country in the
world mainly because of its nature. Fatigue, in general, is very difficult to measure or
observe unlike alcohol and drugs, which have clear key indicators and tests that are
available easily. Probably, the best solutions to this problem are awareness about fatigue-
related accidents and promoting drivers to admit fatigue when needed. The former is
hard and much more expensive to achieve, and the latter is not possible without the
former as driving for long hours is very lucrative.
• Most of the existing systems use external factors and inform the user about the problem
and save users after an accident is accord but from research most of the accidents are
due to faults in users like drowsiness, sleeping while driving.
• These methods can’t able to detect the facial expressions, yawning head nods, and
majorly on eye blink frequencies.
• Accuracy of the existing method is not good when comapred to the proposed model

7. PROPSOED SYTEM:
• Visual object tracking
• Facial landmarks recognition
• Driver drowsiness detection
• Determination of eyes and mouth regions : The region of the eyes, Evaluation of the
driver’s fatigue state
• Eye status recognition: (Recognition based on cnn and recognition based on angle)
• Mouth status recognition
• Alarm Sound
• Self Mode alert

8. Technology Used
• PYTHON - Python is an interpreted, high-level, general-purpose programming language.
Python's design philosophy emphasizes code readability with its notable use of
significant whitespace. Its language constructs and object-oriented approach aim to help
programmers write clear, logical code for small and large-scale projects. Python is
dynamically typed AND supports multiple programming paradigms, including procedural,
object-oriented, and functional programming.
• Pycharm IDE- created to develop open-source software, open-standards, and services for
interactive computing across dozens of programming languages.
• IMAGE PROCESSING - In computer science, digital image processing is the use of
computer algorithms to perform image processing on digital images.
• MACHINE LEARNING - Machine learning is the scientific study of algorithms and
statistical models that computer systems use in order to perform a specific task
effectively without using explicit instructions, relying on patterns and inference instead.
It is seen as a subset of artificial intelligence. Machine learning algorithms build a
mathematical model based on sample data, known as "training data", in order to make
predictions or decisions without being explicitly told.

9. ADVANTAGES:
• This method will detect a problem before any problem accord and
inform the driver and other passengers by raising an alert.
• In this OpenCV based machine learning techniques are used for
automatic detection of drowsiness.

10. LITERATURE REVIEW :
AUTHOR DISCRIPTION ADVANTAGE DISADVANTAGE
1 Ceerthi Bala U.K and
Sarath TV
This system will
provide an alert to the
driver in case of
drowsiness detection
Once it is detected
with the particular
sensor, the system
will alert the driver
Low accuracy
2 Rateb Jabbar et al. developed a
drowsiness detection
model using
Convolutional Neural
Network (CNN) for
mobile application.
When the developed
model applies with
the real time camera,
the drowsiness can
be detected
considerably
As a result, they
found 88% accuracy
without glass, and a
glass system detects
85% accuracy
3 Dr.K.S.Tiwari et al a study to identify
drowsiness detection
with IoT technology
A buzzer and camera
placed with a
microcontroller
continuously monitor
the drowsiness with
the necessary
parameters.
It not detect with
glass.

11. CON……………
S.NO AUTHOR DISCRIPTION ADVANTAGE DISADVANTAGE
4 Dr.K.S.Tiwari e The hear-beat,
temperature, and
alcoholic sensor are
placed with the wearable
device with the driver
A buzzer and camera
placed with a
microcontroller
continuously monitor the
drowsiness with the
necessary parameters.
the buzzer will be alarmed,
and a message will be sent
to the driver in slow
5 Md. Yousuf Hossain and
Fabian Parsia George
.A Raspberry Pi controller
pretends as a hub of this
system. A camera module,
buzzer, and IoT devices
are connected with the
controller
The purpose of IoT in this
2021 International
Conference on
Information system was
to get the mail services.
The camera detects the
driver, and based on the
landmark, it will identify
the drowsiness
Mail sent to other person

12. What is open cv ?
• OpenCV Python is nothing but a wrapper class for the original C++
library to be used with Python.
• Using this, all of the OpenCV array structures gets converted to/from
NumPy arrays.
• This makes it easier to integrate it with other libraries which use
NumPy. For example, libraries such as SciPy and Matplotlib.
• It can process images and videos to identify objects, faces, or even
the handwriting of a human.

13. Block diagram:
camera

15. Flow diagram:

16. Hog algorithm:
• initially, the faces are detected using a Haar Cascade Classifier on an
image in conjunction with the cropping of the cardinal section of the
face. ... The H.O.G(Histogram of Oriented Gradients) is a feature
descriptor used in computer vision for image processing for the
purpose of object detection.
• HOG, or Histogram of Oriented Gradients, is a feature descriptor that
is often used to extract features from image data. It is widely used in
computer vision tasks for object detection. ... This is done by
extracting the gradient and orientation (or you can say magnitude
and direction) of the edges.

17. CON……………….
• The eye aspect Ratio is an estimate of the eye opening state. Based
on Figure 2, the eye aspect ratio can be defined by the below
equation. ... A program can determine if a person's eyes are closed if
the Eye Aspect Ratio falls below a certain threshold. Clmtrackr is
another facial landmark plotter.

18. SOFTWARE REQUIREMENTS
• Operating system: Windows 7.
• Coding Language: python
• Libraries Used
 Numpy
Scipy
Playsound
Dlib
Imutils
opencv, etc.
• Tool: pycham

19. HARDWARE REQUIREMENTS
• Processor: Pentium processer of 400 MHz or higher.
• RAM: minimum 64MB primary memory
• Hard disk: minimum 1 GB hard disk space.
• Monitor : preferable color monitor (16 bit color) and above.
• Web camara
• Compact disk drive
• A keybord and mouse.

20. EYE ASPECT RATIO:
• The Eye Aspect Ratio is an estimate of the eye opening state.
• the eye aspect ratio can be defined by the below equation. ... A
program can determine if a person's eyes are closed if the Eye Aspect
Ratio falls below a certain threshold.
• Clmtrackr is another facial landmark plotter
FORMULA
||P2-P6||+||P3-P5||
EAR= 2||P1-P4||

21. CON………..

22. Facial Landmark:
• Facial Landmark- It is a inbuilt HOG SVM classifier used to determine
the position of 68(x, y) coordinates that map to facial structures on
the face
• It is mainly used for image or video processing and also analysis
including object detection, face detection, etc. Facial landmarks
are used to localize and represent important regions of the face, such
as: · Mouth. · Eyes. · Eyebrows.

23. Facial Landmark:

24. MAR (MOUTH ASPECT RATIO)
• Using this concept, we have calculated the Mouth Aspect Ratio:
Representing the face with 68-(x,y) coordinates. As we see that the
mouth is represented by a set of 20-(x,y) coordinates. So, we have
used coordinates 62, 64, 66, and 68 to calculate the distance between
then in the same way as EAR Calculation.
MAR = |CD| + |EF| + |GH|
3 * |AB|

25. CON………..

26. RESULTS AND DISCUSSION
• The driver anomaly observing framework created is able of identifying laziness,
intoxicated and careless practices of driver in a brief time.
• The Laziness Detecting Framework created based on eye closure of the driver
can separate ordinary eye flicker and tiredness and distinguish the laziness while
driving.
• The suggested device is able to avoid the incidents when driving due to
sleepiness. The system works properly even in case of drivers sporting spectacles
and even below low light stipulations if the digital camera offers higher output.
• Information about the head and eyes position is obtained through a range of
self-developed photograph processing algorithms. During the monitoring, the
system is able to figure out if the eyes are opened or closed.
• When the eyes have been closed for too long, a warning sign is issued.
processing judges the driver’s alertness level on the groundwork of continuous
eye closures

27. Result(Attached your own output)

28. Result(Attached your own output)

29. Result(Attached your own output)

30. Result
• As a result beep sound is heard when the driver yawn and closes the
eye lid. This helps to alert the driver.
• Also self driving mode starts when the driver eye is closed for more
than 60 seconds.

31. CONCLUSION:
• The driver anomaly observing framework created is able of identifying laziness,
intoxicated and careless practices of driver in a brief time. The Laziness Detecting
Framework created based on eye closure of the driver can separate ordinary eye
flicker and tiredness and distinguish the laziness while driving.
• The suggested device is able to avoid the incidents when driving due to
sleepiness. The system works properly even in case of drivers sporting spectacles
and even below low light stipulations if the digital camera offers higher output.
• Information about the head and eyes position is obtained through a range of
self-developed photograph processing algorithms. During the monitoring, the
system is able to figure out if the eyes are opened or closed. When the eyes have
been closed for too long, a warning sign is issued.
• processing judges the driver’s alertness level on the groundwork of continuous
eye closures

32. Limitation
• Dependence on ambient light:- With helpless lighting conditions despite the fact
that face is effectively identified, now and again the framework can't identify the
eyes. So it gives an erroneous result which must be dealt with. Continuously
situation infrared backlights ought to be utilized to maintain a strategic distance
from helpless lighting conditions.
• Optimum range required When the separation among face and webcam isn't at
ideal range then certain issues are emerging.
• At the point when face is away from the webcam (more than 70cm) at that point
the backlight is deficient to light up the face appropriately. So eyes are not
identified with high exactness which shows mistake in detection of laziness.
• Orientation of face
• Problem with multiple faces
• Delay in sounding alarm

33. Future scope:
• The model can be improved incrementally by using other parameter
blinking rate ,state of the cars , etc.
• If all these parameter are used it can improve the accuracy by lot.
• We plan to future work on the project by adding a sensor to o track
the heart rate in order to prevent the accident caused due to sudden
heart attack to driver.
• Same model and techniques can be used for various other uses like
Netflix and other streaming services can detect when is asleep and
stop the video accordingly .
• It can also be used in application that prevent user from sleeping

34. REFERENCE PAPERS:
• [1] World Health Organization, “Global Status Report on Road Safety 2015,” 2015. [Online].
Available: http://www.who.int/violence_injury_prevention/road_safety_status/
2013/en/index.html. [Accessed: 29-May-2017].
• [2] Z. Ngcobo, “Over 1,700 people died on SA roads this festive season,” 2017. [Online].
Available: http://ewn.co.za/2017/01/10/over-1-700-people-died-on-sa-roadsthis- festive-
season. [Accessed: 20-May-2017].
• [3] M. Lindeque, “RTMC report reveals shocking SA road death stats,” 2015. [Online].
Available: http://ewn.co.za/2015/09/11/RTMCreport- reveals-shocking-SA-road-death-stats.
[Accessed: 20-May- 2017].
• [4] Lowveld, “The top 3 causes of accidents?,” 2017. [Online]. Available:
http://lowveld.getitonline.co.za/2017/04/12/top-3-causesaccidents/#. WS0X6WiGPIU.
[Accessed: 20-May-2017].
• [5] “Drowsy Driving.” [Online]. Available: http://sleepcenter.ucla.edu/drowsy-driving.
[Accessed: 22-Jun- 2017].
• [6] “Detection and Prevention : Drowsy Driving – Stay Alert, Arrive Alive.” [Online].
Available: