SlideShare a Scribd company logo
1 of 27
Restricted Circulation | L&T Technology Services | © 2017
2019
Drowsiness state detection of
driver using Eye Lid movement
G.Udhaya
kumar
C.Vignesh
Photo
(Author 2)
Technical Presentation on
Photo
(Author 1)
S.Sathya
Prakash
Photo
(Author 3)
PID No- TG2019002028
Sri Ramakrishna Institute of Technology
Restricted Circulation | L&T Technology Services | © 2017 2PID No.
Index
Challenge Statement
Concept /Scope of Solution
Detailed Description
Pros and Cons of the solution
Technology /background
Validation / Testing / Analysis
Cost /Benefit
1
2
4
3
5
8
9
Conclusion
References12
Implementation/ Proto/POC7
Development Procedure / Methodology6
10 Results and potential Business Impact
11
TG2019002028
Restricted Circulation | L&T Technology Services | © 2017
Restricted Circulation | L&T Technology Services | © 2017 4PID No.
Challenge Statement
TG2019002028
Determination of eye lid opening by driver using MATLAB -SIMULINK modelling technique
To develop a POC for the successful detection of various Eye Lid opening levels and raise
a warning if opening level is so much less when compared with the normal eye open
level with maximum accuracy and performance.
Restricted Circulation | L&T Technology Services | © 2017 5PID No.
Concept / Scope of solution
TG2019002028
To analyse the eye movement and tracking, digital image processing technique is
employed to treat images.
To develop a real-time system inorder to detect the eyelid movement continuously.
The model can,
Be able to process the video continuously while driving.
 State the driver’s drowsiness.
Restricted Circulation | L&T Technology Services | © 2017 6PID No.
Pros and Cons of the solution
TG2019002028
Pros..
Using a small computer named Raspberry PI helps in reduce size and power
consumption.
Light weight code and simple method.
Can be used in dark(in the absence of day light).
Monitoring continuously which helps in avoiding accidents.
Cons..
Face needs to be centred always.
Short battery time, since camera captures while driving.
Restricted Circulation | L&T Technology Services | © 2017 7PID No.
Detailed Description
TG2019002028
To detect and track eye images with complex background, distinctive features of user
eye are used.
The eye tracking is divided into
Face detection and,
Eye region detection
Image Processing technique is implemented here.
The camera is fitted in the dashboard of the car and it starts the recording the driver
while the he/she starts the car.
This video is being stored in 1 TB hard and after the driver removes the key from the slot
the video got erased for storage purpose.
The image is being processed and then the face and eye regions are detected.
By using MATLAB the eye region is identified in the processed image.
The normal eyelid value is set and the eyelid region in the processed image is being
compared with the value provided.
Restricted Circulation | L&T Technology Services | © 2017 8PID No.
Based on the results the drowsiness state of the driver is detected.
Detailed Description
TG2019002028
Video source Face Detection Eyelid Detection
Alarm(or)HMI Drowsiness Detection Eyelid movement
Viola-Jones
algorithm
KLT algorithm
Hough Transform
Raspberry pi
MAT LAB Code
Restricted Circulation | L&T Technology Services | © 2017 9PID No.
Viola-Jones Algorithm:
Object-class detection is a field of computer vision that deals with detection objects that
belong to a particular class – humans, buildings, or cars – in digital videos of images.
The motivation behind Viola-Jones algorithm was to develop an algorithm using which a
computer can successfully detect a face efficiently and accurately.
At least 2 frames per second are processed thus making it a quick and an efficient
algorithm.
The algorithm comprises of four stages:
• Haar Features Selection
• Creating Integral Image
• Adaboost Training Algorithm
• Cascade Classifiers
Detailed Description
TG2019002028
Restricted Circulation | L&T Technology Services | © 2017 10PID No.
Haar-Like Feature:
Haar-like features are digital image features used in object detection.
Haar features are similar to convolution kernels which are used to detect the presence
of a feature in the given image.
The black region in a harr feature is replaced by +1 and white region is replaced by -1.
Adjacent rectangular regions at a specific location in a detection window, sums up the
pixel intensities in each region and calculates the difference between these sums.
Fig: Examples of Haar-Like feature.
Detailed Description
TG2019002028
Restricted Circulation | L&T Technology Services | © 2017 11PID No.
Integral Image:
It is time consuming to sum up all the black region pixels and white region pixels at
every step.
The algorithm introduces the concept of integral image to find the sum of all the pixels
under a rectangle with just 4 corner values instead of summing up all the values.
In generating an integral image the value at pixel is the sum of above and the pixels to
the left.
Integral image allows for calculating of sum of all pixels inside any given rectangle using
only four values at the corners of the rectangle.
1 1 1
1 1 1
1 1 1
1 2 3
2 4 6
3 6 9
TG2019002028
Restricted Circulation | L&T Technology Services | © 2017 12PID No.
Adaboost:
Adaboost is an algorithm which helps in finding only the best features among all the
features.
After these features are found, a weighted combination of all these features is used in
evaluating and deciding if any given window (24x24) has a face or not.
Each of the selected feature is considered to be included if they can at least perform
better than random guessing.
In a standard 24x24 pixel sub-window, there are a 162,336 total of possible features.
Classifier:
Each time the detector’s feature size is different.
Even if an image should contain a face, it is obvious that a large number of sub-windows
evaluated would yield a negative result.
Detailed Description
TG2019002028
Restricted Circulation | L&T Technology Services | © 2017 13PID No.
Contd.,
The algorithm should spend time regions that have high chances of having a face and
should disregard non-faces quickly.
Hence, a single strong classifier that is a combination of all best features is not good to
evaluate on each window because that would lead to a high computation cost.
Therefore a cascade classifier is used which is composed of stages each containing a
strong classifier.
 So all the features are grouped into several stages where each stage has certain number
of features.
The job of each stage is used to determine whether a given sub-window is definitely not
a face or maybe a face.
A given sub-window is immediately discarded as not a face if it fails in any of the stage.
Detailed Description
TG2019002028
Restricted Circulation | L&T Technology Services | © 2017 14PID No.
The KLT Algorithm:
The KLT algorithm helps in tracks the set of feature points across the video frames.
Once the detection locates the face, the next step is to identify the reliably tracked
points.
This uses “good features to track” proposed Tomasi.
When the feature point is tracked, then the system object can be used.
This transformation is applied to the bounding box around the face.
Hough Transform:
This feature is used in image analysis.
In this project it helps in detecting the eyelid movement.
A basic value is set known as Reference Point.
The obtained value should be above the reference point.
Detailed Description
TG2019002028
Restricted Circulation | L&T Technology Services | © 2017 15PID No.
Contd.,
If the obtained value is less than the reference point for a certain time, then it is
confirmed to be drowsiness of the driver.
By obtaining the results from the algorithms the intimation will be given to the external
devices either buzzer or HMI.
This will helps the driver in assisting while driving.
Detailed Description
TG2019002028
Restricted Circulation | L&T Technology Services | © 2017 16PID No.
Technology/Background
TG2019002028
The effective approach of eye detection is to exploit active illumination from infrared(IR)
light emitters.
By using the reflective properties of the pupil when exposed to near infrared light(dark
or bright pupil effects) the eye can be detected and tracked effectively.
The combination of kalman and main shift filtering are applied for eye region tracking.
The Hough transform is used to determine the opening of eyelid level of the driver.
During night time travel, the driver face is illuminated using near-infrared(NIR)
illuminator due to,
It minimizes the impact of different ambient light conditions.
It allows producing the bright pupil effect, which constitutes the foundation for
detection.
As NIR illuminator is barely visible by driver helps in driving smoothly.
Restricted Circulation | L&T Technology Services | © 2017 17PID No.
Development Procedure/Methodology
TG2019002028
TASKS JANUARY FEBRUARY MARCH APRIL
Detecting eye region in the face
of all kind of people.
Measuring the Eye Lid level in the
eye region.
Interfacing the components.
Testing and Implementation
Detection of eye region and eye lid level are done by MAT LAB.
Restricted Circulation | L&T Technology Services | © 2017 18PID No.
Implementation and prototype / POC
TG2019002028
Fig: Detection of face in the image
Face Detection
Feature
Localization
Face NormalizationFace Classification
Still Image
Recognition
result
Restricted Circulation | L&T Technology Services | © 2017 19PID No.
Implementation and prototype / POC
Image Acquistion
Colour Compensation
Face Detection
Eye region
detection &
contour
extraction
Mouth region
detection &
contour extraction
State Analysis
TG2019002028
Restricted Circulation | L&T Technology Services | © 2017 20PID No.
Implementation and prototype / POC
TG2019002028
Restricted Circulation | L&T Technology Services | © 2017 21PID No.
Validation / Testing / Analysis
TG2019002028
The results of drowsiness detection of the driver will be validated by buzzer or HMI
device.
The input image which is captured by camera is being uploaded to the controller where
the image is being processed to determine the face region and the eye region of the
driver.
The eye lid levels from the detected image will be analysed by Hough transform
function.
Based on the results, the buzzer or HMI devices set to go.
Restricted Circulation | L&T Technology Services | © 2017 22PID No.
Cost and benefits
TG2019002028
ITEMS COST
Rental Car or Car Simulator ₹ 35,000 *
Camera ₹ 14,000
Raspberry Pi ₹ 4,000
Hard Disk ₹ 5,000
Buzzer or HMI ₹ 7,000
Infrared(IR) illuminator ₹ 500
Total ₹ 65,500
*The above cost is only for prototype model.
Restricted Circulation | L&T Technology Services | © 2017 23PID No.
Results and potential Business Impact
TG2019002028
For proof of concept, a proto-type of drowsiness detection will be demonstrated in
either car simulator or in a model car.
In product level, the eye lid detection is acheived by Mat Lab simulation implemented in
the raspberry pi module.
At present in the market, this technology is not implied in the cars. The proposed
product may increase the profit of L&T when it released in the market by L&T.
When the proposed system will be designed and fabricated inside the car, it will become
more compact and will be an additional unique feature to ADAS cars. This will provide
potential business impact for L&T because it is like almost safety feature adding to
ADAS.
Restricted Circulation | L&T Technology Services | © 2017 24PID No.
Conclusion
TG2019002028
A proto-type model titled, Drowsiness state detection of driver using Eye Lid
movement” is discussed in the challenge, “Determination of eye lid opening by driver
using MATLAB -SIMULINK modelling technique”.
The challenge/requirement in developing POC for the detection of various eyelid
opening levels is determined and a warning will be given if the opening level is so much
less when compared with the normal eye open level.
The performance and accuracy of the module developed will be maintained as
discussed.
Further by using many HMI interfaces this project can be developed and accidents can
be reduced.
Restricted Circulation | L&T Technology Services | © 2017 25PID No.
References
TG2019002028
Elzohairy Y (2008) Fatal and injury fatigue-related crashes on ontario’s roads: a 5-year
review. In: Working together to understand driver fatigue: report on symposium
proceedings, February 2008
Dingus TA, Jahns SK, Horowitz AD, Knipling R (1998) Human factors design issues for
crash avoidance systems. In: Barfield W, Dingus TA (eds) Human factors in intelligent
transportation systems. Lawrence Associates, Mahwah, pp 55–93
Saito H, Ishiwaka T, Sakata M, Okabayashi S (1994) Applications of driver’s line of sight to
automobiles—what can driver’s eye tell. In: Proceedings of vehicle navigation and
information systems conference, Yokohama, Japan, pp 21–26
Ueno H, Kaneda M, Tsukino M (1994) Development of drowsiness detection system. In
Proceedings of vehicle navigation and information systems conference, Yokohama,
Japan, pp 15–20
Boverie S, Leqellec JM, Hirl A (1998) Intelligent systems for video monitoring of vehicle
cockpit. In: International Congress and exposition ITS: advanced controls and vehicle
navigation systems, pp 1–5
Restricted Circulation | L&T Technology Services | © 2017 26PID No.
Kaneda M et al (1994) Development of a drowsiness warning system. In: The 11th
international conference on enhanced safety of vehicle, Munich
Onken R (1994) Daisy, an adaptive knowledge-based driver monitoring and warning
system. In: Proceedings of vehicle navigation and information systems conference,
Yokohama, Japan, pp 3–10
Feraric J, Kopf M, Onken R (1992) Statistical versus neural bet approach for driver
behaviour description and adaptive warning. The 11th European annual manual, pp
429–436
Ishii T, Hirose M, Iwata H (1987) Automatic recognition of driver’s facial expression by
image analysis. J Soc Automot Eng Jap 41:1398–1403
Yammamoto K, Higuchi S (1992) Development of a drowsiness warning system. J Soc
Automot Eng Jap 46:127–133
References
TG2019002028
Restricted Circulation | L&T Technology Services | © 2017
THANK YOU

More Related Content

What's hot

Automated Driver Fatigue Detection
Automated Driver Fatigue DetectionAutomated Driver Fatigue Detection
Automated Driver Fatigue DetectionArman Hossain
 
Driver fatigue detection system
Driver fatigue detection systemDriver fatigue detection system
Driver fatigue detection systemYASH TILVA
 
Driver drowsiness detection
Driver drowsiness detectionDriver drowsiness detection
Driver drowsiness detectionConnecting Point
 
Vision based system for monitoring the loss of attention in automotive driver
Vision based system for monitoring the loss of attention in automotive driverVision based system for monitoring the loss of attention in automotive driver
Vision based system for monitoring the loss of attention in automotive driverVinay Diddi
 
Driver DrowsiNess System
Driver DrowsiNess SystemDriver DrowsiNess System
Driver DrowsiNess SystemGurunadh Guru
 
Real Time Eye Blinking and Yawning Detection
Real Time Eye Blinking and Yawning DetectionReal Time Eye Blinking and Yawning Detection
Real Time Eye Blinking and Yawning Detectionijtsrd
 
Drowsiness detection ppt
Drowsiness detection pptDrowsiness detection ppt
Drowsiness detection pptsafepassage
 
Driver Drowsiness Detection Review
Driver Drowsiness Detection ReviewDriver Drowsiness Detection Review
Driver Drowsiness Detection ReviewAsaad Waqar
 
Driver Drowsiness Detection report
Driver Drowsiness Detection reportDriver Drowsiness Detection report
Driver Drowsiness Detection reportPurvanshJain1
 
Driver detection system_final.ppt
Driver detection system_final.pptDriver detection system_final.ppt
Driver detection system_final.pptMaseeraAhmed1
 
AGE AND GENDER DETECTION.pptx
AGE AND GENDER DETECTION.pptxAGE AND GENDER DETECTION.pptx
AGE AND GENDER DETECTION.pptxssuserb4a9ba
 
Self Driving Autopilot Car
Self Driving Autopilot CarSelf Driving Autopilot Car
Self Driving Autopilot CarVaibhav Koli
 
Driver Fatigue Monitoring System Using Eye Closure
Driver Fatigue Monitoring System Using Eye ClosureDriver Fatigue Monitoring System Using Eye Closure
Driver Fatigue Monitoring System Using Eye ClosureIJMER
 
Human age and gender Detection
Human age and gender DetectionHuman age and gender Detection
Human age and gender DetectionAbhiAchalla
 
Vehicle number plate recognition using matlab
Vehicle number plate recognition using matlabVehicle number plate recognition using matlab
Vehicle number plate recognition using matlabKongara Sudharshan
 
Artificial intelligence in autonomous vehicle
Artificial intelligence in autonomous vehicleArtificial intelligence in autonomous vehicle
Artificial intelligence in autonomous vehicleGwenaël C
 
Driver Drowsiness Detection Using Matlab
Driver Drowsiness Detection Using MatlabDriver Drowsiness Detection Using Matlab
Driver Drowsiness Detection Using MatlabHanojhan Rajahrajasingh
 

What's hot (20)

Automated Driver Fatigue Detection
Automated Driver Fatigue DetectionAutomated Driver Fatigue Detection
Automated Driver Fatigue Detection
 
Driver fatigue detection system
Driver fatigue detection systemDriver fatigue detection system
Driver fatigue detection system
 
Driver drowsiness detection
Driver drowsiness detectionDriver drowsiness detection
Driver drowsiness detection
 
Vision based system for monitoring the loss of attention in automotive driver
Vision based system for monitoring the loss of attention in automotive driverVision based system for monitoring the loss of attention in automotive driver
Vision based system for monitoring the loss of attention in automotive driver
 
DRIVER DROWSINESS ALERT SYSTEM
DRIVER DROWSINESS ALERT SYSTEMDRIVER DROWSINESS ALERT SYSTEM
DRIVER DROWSINESS ALERT SYSTEM
 
Driver DrowsiNess System
Driver DrowsiNess SystemDriver DrowsiNess System
Driver DrowsiNess System
 
Real Time Eye Blinking and Yawning Detection
Real Time Eye Blinking and Yawning DetectionReal Time Eye Blinking and Yawning Detection
Real Time Eye Blinking and Yawning Detection
 
Drowsiness detection ppt
Drowsiness detection pptDrowsiness detection ppt
Drowsiness detection ppt
 
Driver Drowsiness Detection Review
Driver Drowsiness Detection ReviewDriver Drowsiness Detection Review
Driver Drowsiness Detection Review
 
Driver Drowsiness Detection report
Driver Drowsiness Detection reportDriver Drowsiness Detection report
Driver Drowsiness Detection report
 
Driver detection system_final.ppt
Driver detection system_final.pptDriver detection system_final.ppt
Driver detection system_final.ppt
 
Adaptive cruise control’
Adaptive cruise control’Adaptive cruise control’
Adaptive cruise control’
 
Self driving cars
Self driving carsSelf driving cars
Self driving cars
 
AGE AND GENDER DETECTION.pptx
AGE AND GENDER DETECTION.pptxAGE AND GENDER DETECTION.pptx
AGE AND GENDER DETECTION.pptx
 
Self Driving Autopilot Car
Self Driving Autopilot CarSelf Driving Autopilot Car
Self Driving Autopilot Car
 
Driver Fatigue Monitoring System Using Eye Closure
Driver Fatigue Monitoring System Using Eye ClosureDriver Fatigue Monitoring System Using Eye Closure
Driver Fatigue Monitoring System Using Eye Closure
 
Human age and gender Detection
Human age and gender DetectionHuman age and gender Detection
Human age and gender Detection
 
Vehicle number plate recognition using matlab
Vehicle number plate recognition using matlabVehicle number plate recognition using matlab
Vehicle number plate recognition using matlab
 
Artificial intelligence in autonomous vehicle
Artificial intelligence in autonomous vehicleArtificial intelligence in autonomous vehicle
Artificial intelligence in autonomous vehicle
 
Driver Drowsiness Detection Using Matlab
Driver Drowsiness Detection Using MatlabDriver Drowsiness Detection Using Matlab
Driver Drowsiness Detection Using Matlab
 

Similar to Driver Drowsiness Detection Using Eye Lid Movement

DROWSINESS DETECTION MODEL USING PYTHON
DROWSINESS DETECTION MODEL USING PYTHONDROWSINESS DETECTION MODEL USING PYTHON
DROWSINESS DETECTION MODEL USING PYTHONIRJET Journal
 
IRJET- Face Detection and Tracking Algorithm using Open CV with Raspberry Pi
IRJET- Face Detection and Tracking Algorithm using Open CV with Raspberry PiIRJET- Face Detection and Tracking Algorithm using Open CV with Raspberry Pi
IRJET- Face Detection and Tracking Algorithm using Open CV with Raspberry PiIRJET Journal
 
IRJET- Drive Assistance an Android Application for Drowsiness Detection
IRJET- Drive Assistance an Android Application for Drowsiness DetectionIRJET- Drive Assistance an Android Application for Drowsiness Detection
IRJET- Drive Assistance an Android Application for Drowsiness DetectionIRJET Journal
 
IRJET- Traffic Sign and Drowsiness Detection using Open-CV
IRJET- Traffic Sign and Drowsiness Detection using Open-CVIRJET- Traffic Sign and Drowsiness Detection using Open-CV
IRJET- Traffic Sign and Drowsiness Detection using Open-CVIRJET Journal
 
REAL TIME DROWSINESS DETECTION
REAL TIME DROWSINESS DETECTIONREAL TIME DROWSINESS DETECTION
REAL TIME DROWSINESS DETECTIONIRJET Journal
 
IRJET- Driver’s Sleep Detection
IRJET-  	  Driver’s Sleep DetectionIRJET-  	  Driver’s Sleep Detection
IRJET- Driver’s Sleep DetectionIRJET Journal
 
Different Methodologies for Indian License Plate Detection
Different Methodologies for Indian License Plate DetectionDifferent Methodologies for Indian License Plate Detection
Different Methodologies for Indian License Plate DetectionIRJET Journal
 
IRJET- Drivers Stupor Scrutinizing System
IRJET-  	  Drivers Stupor Scrutinizing SystemIRJET-  	  Drivers Stupor Scrutinizing System
IRJET- Drivers Stupor Scrutinizing SystemIRJET Journal
 
Implementation of face and eye detection on DM6437 board using simulink model
Implementation of face and eye detection on DM6437 board using simulink modelImplementation of face and eye detection on DM6437 board using simulink model
Implementation of face and eye detection on DM6437 board using simulink modeljournalBEEI
 
Face detection and tracking in a video sequence
Face detection and tracking in a video sequenceFace detection and tracking in a video sequence
Face detection and tracking in a video sequenceKarthik G N
 
IRJET- Robust Visual Analysis of Eye State
IRJET-  	  Robust Visual Analysis of Eye StateIRJET-  	  Robust Visual Analysis of Eye State
IRJET- Robust Visual Analysis of Eye StateIRJET Journal
 
IRJET- Real-Time Partial Face Occlusion Detection using Matlab
IRJET-	 Real-Time Partial Face Occlusion Detection using MatlabIRJET-	 Real-Time Partial Face Occlusion Detection using Matlab
IRJET- Real-Time Partial Face Occlusion Detection using MatlabIRJET Journal
 
eagleeye-151129054531-lva1-app6892.pptx
eagleeye-151129054531-lva1-app6892.pptxeagleeye-151129054531-lva1-app6892.pptx
eagleeye-151129054531-lva1-app6892.pptxKGANESH34
 
COMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLAB
COMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLABCOMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLAB
COMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLABIRJET Journal
 
Licence Plate Recognition Using Supervised Learning and Deep Learning
Licence Plate Recognition Using Supervised Learning and Deep LearningLicence Plate Recognition Using Supervised Learning and Deep Learning
Licence Plate Recognition Using Supervised Learning and Deep LearningIRJET Journal
 
IRJET- Smart Traffic Control System using Image Processing
IRJET- Smart Traffic Control System using Image ProcessingIRJET- Smart Traffic Control System using Image Processing
IRJET- Smart Traffic Control System using Image ProcessingIRJET Journal
 
IRJET- Video Based Traffic Sign Detection by Scale Based Frame Fusion Technique
IRJET- Video Based Traffic Sign Detection by Scale Based Frame Fusion TechniqueIRJET- Video Based Traffic Sign Detection by Scale Based Frame Fusion Technique
IRJET- Video Based Traffic Sign Detection by Scale Based Frame Fusion TechniqueIRJET Journal
 
IRJET- Driver Alert System to Detect Drowsiness and Distraction
IRJET- Driver Alert System to Detect Drowsiness and DistractionIRJET- Driver Alert System to Detect Drowsiness and Distraction
IRJET- Driver Alert System to Detect Drowsiness and DistractionIRJET Journal
 

Similar to Driver Drowsiness Detection Using Eye Lid Movement (20)

DROWSINESS DETECTION MODEL USING PYTHON
DROWSINESS DETECTION MODEL USING PYTHONDROWSINESS DETECTION MODEL USING PYTHON
DROWSINESS DETECTION MODEL USING PYTHON
 
IRJET- Face Detection and Tracking Algorithm using Open CV with Raspberry Pi
IRJET- Face Detection and Tracking Algorithm using Open CV with Raspberry PiIRJET- Face Detection and Tracking Algorithm using Open CV with Raspberry Pi
IRJET- Face Detection and Tracking Algorithm using Open CV with Raspberry Pi
 
IRJET- Drive Assistance an Android Application for Drowsiness Detection
IRJET- Drive Assistance an Android Application for Drowsiness DetectionIRJET- Drive Assistance an Android Application for Drowsiness Detection
IRJET- Drive Assistance an Android Application for Drowsiness Detection
 
IRJET- Traffic Sign and Drowsiness Detection using Open-CV
IRJET- Traffic Sign and Drowsiness Detection using Open-CVIRJET- Traffic Sign and Drowsiness Detection using Open-CV
IRJET- Traffic Sign and Drowsiness Detection using Open-CV
 
REAL TIME DROWSINESS DETECTION
REAL TIME DROWSINESS DETECTIONREAL TIME DROWSINESS DETECTION
REAL TIME DROWSINESS DETECTION
 
IRJET- Driver’s Sleep Detection
IRJET-  	  Driver’s Sleep DetectionIRJET-  	  Driver’s Sleep Detection
IRJET- Driver’s Sleep Detection
 
Different Methodologies for Indian License Plate Detection
Different Methodologies for Indian License Plate DetectionDifferent Methodologies for Indian License Plate Detection
Different Methodologies for Indian License Plate Detection
 
IRJET- Drivers Stupor Scrutinizing System
IRJET-  	  Drivers Stupor Scrutinizing SystemIRJET-  	  Drivers Stupor Scrutinizing System
IRJET- Drivers Stupor Scrutinizing System
 
Implementation of face and eye detection on DM6437 board using simulink model
Implementation of face and eye detection on DM6437 board using simulink modelImplementation of face and eye detection on DM6437 board using simulink model
Implementation of face and eye detection on DM6437 board using simulink model
 
A Proposed Accident Preventive Model For Smart Vehicles
A Proposed Accident Preventive Model For Smart VehiclesA Proposed Accident Preventive Model For Smart Vehicles
A Proposed Accident Preventive Model For Smart Vehicles
 
Face detection and tracking in a video sequence
Face detection and tracking in a video sequenceFace detection and tracking in a video sequence
Face detection and tracking in a video sequence
 
IRJET- Robust Visual Analysis of Eye State
IRJET-  	  Robust Visual Analysis of Eye StateIRJET-  	  Robust Visual Analysis of Eye State
IRJET- Robust Visual Analysis of Eye State
 
IRJET- Real-Time Partial Face Occlusion Detection using Matlab
IRJET-	 Real-Time Partial Face Occlusion Detection using MatlabIRJET-	 Real-Time Partial Face Occlusion Detection using Matlab
IRJET- Real-Time Partial Face Occlusion Detection using Matlab
 
eagleeye-151129054531-lva1-app6892.pptx
eagleeye-151129054531-lva1-app6892.pptxeagleeye-151129054531-lva1-app6892.pptx
eagleeye-151129054531-lva1-app6892.pptx
 
COMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLAB
COMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLABCOMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLAB
COMPARATIVE STUDY ON AUTOMATED NUMBER PLATE EXTRACTION USING OPEN CV AND MATLAB
 
Licence Plate Recognition Using Supervised Learning and Deep Learning
Licence Plate Recognition Using Supervised Learning and Deep LearningLicence Plate Recognition Using Supervised Learning and Deep Learning
Licence Plate Recognition Using Supervised Learning and Deep Learning
 
IRJET- Smart Traffic Control System using Image Processing
IRJET- Smart Traffic Control System using Image ProcessingIRJET- Smart Traffic Control System using Image Processing
IRJET- Smart Traffic Control System using Image Processing
 
IRJET- Video Based Traffic Sign Detection by Scale Based Frame Fusion Technique
IRJET- Video Based Traffic Sign Detection by Scale Based Frame Fusion TechniqueIRJET- Video Based Traffic Sign Detection by Scale Based Frame Fusion Technique
IRJET- Video Based Traffic Sign Detection by Scale Based Frame Fusion Technique
 
IRJET- Driver Alert System to Detect Drowsiness and Distraction
IRJET- Driver Alert System to Detect Drowsiness and DistractionIRJET- Driver Alert System to Detect Drowsiness and Distraction
IRJET- Driver Alert System to Detect Drowsiness and Distraction
 
DROWSINESS DETECTION SYSTEM USING MACHINE LEARNING
DROWSINESS DETECTION SYSTEM USING MACHINE LEARNINGDROWSINESS DETECTION SYSTEM USING MACHINE LEARNING
DROWSINESS DETECTION SYSTEM USING MACHINE LEARNING
 

Recently uploaded

如何办理爱尔兰都柏林大学毕业证(UCD毕业证) 成绩单原版一比一
如何办理爱尔兰都柏林大学毕业证(UCD毕业证) 成绩单原版一比一如何办理爱尔兰都柏林大学毕业证(UCD毕业证) 成绩单原版一比一
如何办理爱尔兰都柏林大学毕业证(UCD毕业证) 成绩单原版一比一mjyguplun
 
Dubai Call Girls Size E6 (O525547819) Call Girls In Dubai
Dubai Call Girls  Size E6 (O525547819) Call Girls In DubaiDubai Call Girls  Size E6 (O525547819) Call Girls In Dubai
Dubai Call Girls Size E6 (O525547819) Call Girls In Dubaikojalkojal131
 
如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一
如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一
如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一hnfusn
 
Call Girl Service Global Village Dubai +971509430017 Independent Call Girls G...
Call Girl Service Global Village Dubai +971509430017 Independent Call Girls G...Call Girl Service Global Village Dubai +971509430017 Independent Call Girls G...
Call Girl Service Global Village Dubai +971509430017 Independent Call Girls G...kexey39068
 
2024 TOP 10 most fuel-efficient vehicles according to the US agency
2024 TOP 10 most fuel-efficient vehicles according to the US agency2024 TOP 10 most fuel-efficient vehicles according to the US agency
2024 TOP 10 most fuel-efficient vehicles according to the US agencyHyundai Motor Group
 
FULL ENJOY - 9953040155 Call Girls in Sector 61 | Noida
FULL ENJOY - 9953040155 Call Girls in Sector 61 | NoidaFULL ENJOY - 9953040155 Call Girls in Sector 61 | Noida
FULL ENJOY - 9953040155 Call Girls in Sector 61 | NoidaMalviyaNagarCallGirl
 
定制(Plymouth文凭证书)普利茅斯大学毕业证毕业证成绩单学历认证原版一比一
定制(Plymouth文凭证书)普利茅斯大学毕业证毕业证成绩单学历认证原版一比一定制(Plymouth文凭证书)普利茅斯大学毕业证毕业证成绩单学历认证原版一比一
定制(Plymouth文凭证书)普利茅斯大学毕业证毕业证成绩单学历认证原版一比一fhhkjh
 
BLUE VEHICLES the kids picture show 2024
BLUE VEHICLES the kids picture show 2024BLUE VEHICLES the kids picture show 2024
BLUE VEHICLES the kids picture show 2024AHOhOops1
 
( Best ) Genuine Call Girls In Mandi House =DELHI-| 8377087607
( Best ) Genuine Call Girls In Mandi House =DELHI-| 8377087607( Best ) Genuine Call Girls In Mandi House =DELHI-| 8377087607
( Best ) Genuine Call Girls In Mandi House =DELHI-| 8377087607dollysharma2066
 
(8264348440) 🔝 Call Girls In Shaheen Bagh 🔝 Delhi NCR
(8264348440) 🔝 Call Girls In Shaheen Bagh 🔝 Delhi NCR(8264348440) 🔝 Call Girls In Shaheen Bagh 🔝 Delhi NCR
(8264348440) 🔝 Call Girls In Shaheen Bagh 🔝 Delhi NCRsoniya singh
 
UNIT-II-ENGINE AUXILIARY SYSTEMS &TURBOCHARGER
UNIT-II-ENGINE AUXILIARY SYSTEMS &TURBOCHARGERUNIT-II-ENGINE AUXILIARY SYSTEMS &TURBOCHARGER
UNIT-II-ENGINE AUXILIARY SYSTEMS &TURBOCHARGERDineshKumar4165
 
定制昆士兰大学毕业证(本硕)UQ学位证书原版一比一
定制昆士兰大学毕业证(本硕)UQ学位证书原版一比一定制昆士兰大学毕业证(本硕)UQ学位证书原版一比一
定制昆士兰大学毕业证(本硕)UQ学位证书原版一比一fjjhfuubb
 
call girls in G.T.B. Nagar (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in  G.T.B. Nagar (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️call girls in  G.T.B. Nagar (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in G.T.B. Nagar (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
call girls in Jama Masjid (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Jama Masjid (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️call girls in Jama Masjid (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Jama Masjid (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
UNIT-1-VEHICLE STRUCTURE AND ENGINES.ppt
UNIT-1-VEHICLE STRUCTURE AND ENGINES.pptUNIT-1-VEHICLE STRUCTURE AND ENGINES.ppt
UNIT-1-VEHICLE STRUCTURE AND ENGINES.pptDineshKumar4165
 
(办理学位证)(Toledo毕业证)托莱多大学毕业证成绩单修改留信学历认证原版一模一样
(办理学位证)(Toledo毕业证)托莱多大学毕业证成绩单修改留信学历认证原版一模一样(办理学位证)(Toledo毕业证)托莱多大学毕业证成绩单修改留信学历认证原版一模一样
(办理学位证)(Toledo毕业证)托莱多大学毕业证成绩单修改留信学历认证原版一模一样gfghbihg
 
原版工艺美国普林斯顿大学毕业证Princeton毕业证成绩单修改留信学历认证
原版工艺美国普林斯顿大学毕业证Princeton毕业证成绩单修改留信学历认证原版工艺美国普林斯顿大学毕业证Princeton毕业证成绩单修改留信学历认证
原版工艺美国普林斯顿大学毕业证Princeton毕业证成绩单修改留信学历认证jjrehjwj11gg
 

Recently uploaded (20)

Indian Downtown Call Girls # 00971528903066 # Indian Call Girls In Downtown D...
Indian Downtown Call Girls # 00971528903066 # Indian Call Girls In Downtown D...Indian Downtown Call Girls # 00971528903066 # Indian Call Girls In Downtown D...
Indian Downtown Call Girls # 00971528903066 # Indian Call Girls In Downtown D...
 
Hot Sexy call girls in Pira Garhi🔝 9953056974 🔝 escort Service
Hot Sexy call girls in Pira Garhi🔝 9953056974 🔝 escort ServiceHot Sexy call girls in Pira Garhi🔝 9953056974 🔝 escort Service
Hot Sexy call girls in Pira Garhi🔝 9953056974 🔝 escort Service
 
如何办理爱尔兰都柏林大学毕业证(UCD毕业证) 成绩单原版一比一
如何办理爱尔兰都柏林大学毕业证(UCD毕业证) 成绩单原版一比一如何办理爱尔兰都柏林大学毕业证(UCD毕业证) 成绩单原版一比一
如何办理爱尔兰都柏林大学毕业证(UCD毕业证) 成绩单原版一比一
 
Dubai Call Girls Size E6 (O525547819) Call Girls In Dubai
Dubai Call Girls  Size E6 (O525547819) Call Girls In DubaiDubai Call Girls  Size E6 (O525547819) Call Girls In Dubai
Dubai Call Girls Size E6 (O525547819) Call Girls In Dubai
 
如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一
如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一
如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一
 
Call Girl Service Global Village Dubai +971509430017 Independent Call Girls G...
Call Girl Service Global Village Dubai +971509430017 Independent Call Girls G...Call Girl Service Global Village Dubai +971509430017 Independent Call Girls G...
Call Girl Service Global Village Dubai +971509430017 Independent Call Girls G...
 
2024 TOP 10 most fuel-efficient vehicles according to the US agency
2024 TOP 10 most fuel-efficient vehicles according to the US agency2024 TOP 10 most fuel-efficient vehicles according to the US agency
2024 TOP 10 most fuel-efficient vehicles according to the US agency
 
FULL ENJOY - 9953040155 Call Girls in Sector 61 | Noida
FULL ENJOY - 9953040155 Call Girls in Sector 61 | NoidaFULL ENJOY - 9953040155 Call Girls in Sector 61 | Noida
FULL ENJOY - 9953040155 Call Girls in Sector 61 | Noida
 
定制(Plymouth文凭证书)普利茅斯大学毕业证毕业证成绩单学历认证原版一比一
定制(Plymouth文凭证书)普利茅斯大学毕业证毕业证成绩单学历认证原版一比一定制(Plymouth文凭证书)普利茅斯大学毕业证毕业证成绩单学历认证原版一比一
定制(Plymouth文凭证书)普利茅斯大学毕业证毕业证成绩单学历认证原版一比一
 
BLUE VEHICLES the kids picture show 2024
BLUE VEHICLES the kids picture show 2024BLUE VEHICLES the kids picture show 2024
BLUE VEHICLES the kids picture show 2024
 
( Best ) Genuine Call Girls In Mandi House =DELHI-| 8377087607
( Best ) Genuine Call Girls In Mandi House =DELHI-| 8377087607( Best ) Genuine Call Girls In Mandi House =DELHI-| 8377087607
( Best ) Genuine Call Girls In Mandi House =DELHI-| 8377087607
 
(8264348440) 🔝 Call Girls In Shaheen Bagh 🔝 Delhi NCR
(8264348440) 🔝 Call Girls In Shaheen Bagh 🔝 Delhi NCR(8264348440) 🔝 Call Girls In Shaheen Bagh 🔝 Delhi NCR
(8264348440) 🔝 Call Girls In Shaheen Bagh 🔝 Delhi NCR
 
UNIT-II-ENGINE AUXILIARY SYSTEMS &TURBOCHARGER
UNIT-II-ENGINE AUXILIARY SYSTEMS &TURBOCHARGERUNIT-II-ENGINE AUXILIARY SYSTEMS &TURBOCHARGER
UNIT-II-ENGINE AUXILIARY SYSTEMS &TURBOCHARGER
 
定制昆士兰大学毕业证(本硕)UQ学位证书原版一比一
定制昆士兰大学毕业证(本硕)UQ学位证书原版一比一定制昆士兰大学毕业证(本硕)UQ学位证书原版一比一
定制昆士兰大学毕业证(本硕)UQ学位证书原版一比一
 
call girls in G.T.B. Nagar (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in  G.T.B. Nagar (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️call girls in  G.T.B. Nagar (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in G.T.B. Nagar (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
 
call girls in Jama Masjid (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Jama Masjid (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️call girls in Jama Masjid (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
call girls in Jama Masjid (DELHI) 🔝 >༒9953330565🔝 genuine Escort Service 🔝✔️✔️
 
UNIT-1-VEHICLE STRUCTURE AND ENGINES.ppt
UNIT-1-VEHICLE STRUCTURE AND ENGINES.pptUNIT-1-VEHICLE STRUCTURE AND ENGINES.ppt
UNIT-1-VEHICLE STRUCTURE AND ENGINES.ppt
 
(办理学位证)(Toledo毕业证)托莱多大学毕业证成绩单修改留信学历认证原版一模一样
(办理学位证)(Toledo毕业证)托莱多大学毕业证成绩单修改留信学历认证原版一模一样(办理学位证)(Toledo毕业证)托莱多大学毕业证成绩单修改留信学历认证原版一模一样
(办理学位证)(Toledo毕业证)托莱多大学毕业证成绩单修改留信学历认证原版一模一样
 
sauth delhi call girls in Connaught Place🔝 9953056974 🔝 escort Service
sauth delhi call girls in  Connaught Place🔝 9953056974 🔝 escort Servicesauth delhi call girls in  Connaught Place🔝 9953056974 🔝 escort Service
sauth delhi call girls in Connaught Place🔝 9953056974 🔝 escort Service
 
原版工艺美国普林斯顿大学毕业证Princeton毕业证成绩单修改留信学历认证
原版工艺美国普林斯顿大学毕业证Princeton毕业证成绩单修改留信学历认证原版工艺美国普林斯顿大学毕业证Princeton毕业证成绩单修改留信学历认证
原版工艺美国普林斯顿大学毕业证Princeton毕业证成绩单修改留信学历认证
 

Driver Drowsiness Detection Using Eye Lid Movement

  • 1. Restricted Circulation | L&T Technology Services | © 2017 2019 Drowsiness state detection of driver using Eye Lid movement G.Udhaya kumar C.Vignesh Photo (Author 2) Technical Presentation on Photo (Author 1) S.Sathya Prakash Photo (Author 3) PID No- TG2019002028 Sri Ramakrishna Institute of Technology
  • 2. Restricted Circulation | L&T Technology Services | © 2017 2PID No. Index Challenge Statement Concept /Scope of Solution Detailed Description Pros and Cons of the solution Technology /background Validation / Testing / Analysis Cost /Benefit 1 2 4 3 5 8 9 Conclusion References12 Implementation/ Proto/POC7 Development Procedure / Methodology6 10 Results and potential Business Impact 11 TG2019002028
  • 3. Restricted Circulation | L&T Technology Services | © 2017
  • 4. Restricted Circulation | L&T Technology Services | © 2017 4PID No. Challenge Statement TG2019002028 Determination of eye lid opening by driver using MATLAB -SIMULINK modelling technique To develop a POC for the successful detection of various Eye Lid opening levels and raise a warning if opening level is so much less when compared with the normal eye open level with maximum accuracy and performance.
  • 5. Restricted Circulation | L&T Technology Services | © 2017 5PID No. Concept / Scope of solution TG2019002028 To analyse the eye movement and tracking, digital image processing technique is employed to treat images. To develop a real-time system inorder to detect the eyelid movement continuously. The model can, Be able to process the video continuously while driving.  State the driver’s drowsiness.
  • 6. Restricted Circulation | L&T Technology Services | © 2017 6PID No. Pros and Cons of the solution TG2019002028 Pros.. Using a small computer named Raspberry PI helps in reduce size and power consumption. Light weight code and simple method. Can be used in dark(in the absence of day light). Monitoring continuously which helps in avoiding accidents. Cons.. Face needs to be centred always. Short battery time, since camera captures while driving.
  • 7. Restricted Circulation | L&T Technology Services | © 2017 7PID No. Detailed Description TG2019002028 To detect and track eye images with complex background, distinctive features of user eye are used. The eye tracking is divided into Face detection and, Eye region detection Image Processing technique is implemented here. The camera is fitted in the dashboard of the car and it starts the recording the driver while the he/she starts the car. This video is being stored in 1 TB hard and after the driver removes the key from the slot the video got erased for storage purpose. The image is being processed and then the face and eye regions are detected. By using MATLAB the eye region is identified in the processed image. The normal eyelid value is set and the eyelid region in the processed image is being compared with the value provided.
  • 8. Restricted Circulation | L&T Technology Services | © 2017 8PID No. Based on the results the drowsiness state of the driver is detected. Detailed Description TG2019002028 Video source Face Detection Eyelid Detection Alarm(or)HMI Drowsiness Detection Eyelid movement Viola-Jones algorithm KLT algorithm Hough Transform Raspberry pi MAT LAB Code
  • 9. Restricted Circulation | L&T Technology Services | © 2017 9PID No. Viola-Jones Algorithm: Object-class detection is a field of computer vision that deals with detection objects that belong to a particular class – humans, buildings, or cars – in digital videos of images. The motivation behind Viola-Jones algorithm was to develop an algorithm using which a computer can successfully detect a face efficiently and accurately. At least 2 frames per second are processed thus making it a quick and an efficient algorithm. The algorithm comprises of four stages: • Haar Features Selection • Creating Integral Image • Adaboost Training Algorithm • Cascade Classifiers Detailed Description TG2019002028
  • 10. Restricted Circulation | L&T Technology Services | © 2017 10PID No. Haar-Like Feature: Haar-like features are digital image features used in object detection. Haar features are similar to convolution kernels which are used to detect the presence of a feature in the given image. The black region in a harr feature is replaced by +1 and white region is replaced by -1. Adjacent rectangular regions at a specific location in a detection window, sums up the pixel intensities in each region and calculates the difference between these sums. Fig: Examples of Haar-Like feature. Detailed Description TG2019002028
  • 11. Restricted Circulation | L&T Technology Services | © 2017 11PID No. Integral Image: It is time consuming to sum up all the black region pixels and white region pixels at every step. The algorithm introduces the concept of integral image to find the sum of all the pixels under a rectangle with just 4 corner values instead of summing up all the values. In generating an integral image the value at pixel is the sum of above and the pixels to the left. Integral image allows for calculating of sum of all pixels inside any given rectangle using only four values at the corners of the rectangle. 1 1 1 1 1 1 1 1 1 1 2 3 2 4 6 3 6 9 TG2019002028
  • 12. Restricted Circulation | L&T Technology Services | © 2017 12PID No. Adaboost: Adaboost is an algorithm which helps in finding only the best features among all the features. After these features are found, a weighted combination of all these features is used in evaluating and deciding if any given window (24x24) has a face or not. Each of the selected feature is considered to be included if they can at least perform better than random guessing. In a standard 24x24 pixel sub-window, there are a 162,336 total of possible features. Classifier: Each time the detector’s feature size is different. Even if an image should contain a face, it is obvious that a large number of sub-windows evaluated would yield a negative result. Detailed Description TG2019002028
  • 13. Restricted Circulation | L&T Technology Services | © 2017 13PID No. Contd., The algorithm should spend time regions that have high chances of having a face and should disregard non-faces quickly. Hence, a single strong classifier that is a combination of all best features is not good to evaluate on each window because that would lead to a high computation cost. Therefore a cascade classifier is used which is composed of stages each containing a strong classifier.  So all the features are grouped into several stages where each stage has certain number of features. The job of each stage is used to determine whether a given sub-window is definitely not a face or maybe a face. A given sub-window is immediately discarded as not a face if it fails in any of the stage. Detailed Description TG2019002028
  • 14. Restricted Circulation | L&T Technology Services | © 2017 14PID No. The KLT Algorithm: The KLT algorithm helps in tracks the set of feature points across the video frames. Once the detection locates the face, the next step is to identify the reliably tracked points. This uses “good features to track” proposed Tomasi. When the feature point is tracked, then the system object can be used. This transformation is applied to the bounding box around the face. Hough Transform: This feature is used in image analysis. In this project it helps in detecting the eyelid movement. A basic value is set known as Reference Point. The obtained value should be above the reference point. Detailed Description TG2019002028
  • 15. Restricted Circulation | L&T Technology Services | © 2017 15PID No. Contd., If the obtained value is less than the reference point for a certain time, then it is confirmed to be drowsiness of the driver. By obtaining the results from the algorithms the intimation will be given to the external devices either buzzer or HMI. This will helps the driver in assisting while driving. Detailed Description TG2019002028
  • 16. Restricted Circulation | L&T Technology Services | © 2017 16PID No. Technology/Background TG2019002028 The effective approach of eye detection is to exploit active illumination from infrared(IR) light emitters. By using the reflective properties of the pupil when exposed to near infrared light(dark or bright pupil effects) the eye can be detected and tracked effectively. The combination of kalman and main shift filtering are applied for eye region tracking. The Hough transform is used to determine the opening of eyelid level of the driver. During night time travel, the driver face is illuminated using near-infrared(NIR) illuminator due to, It minimizes the impact of different ambient light conditions. It allows producing the bright pupil effect, which constitutes the foundation for detection. As NIR illuminator is barely visible by driver helps in driving smoothly.
  • 17. Restricted Circulation | L&T Technology Services | © 2017 17PID No. Development Procedure/Methodology TG2019002028 TASKS JANUARY FEBRUARY MARCH APRIL Detecting eye region in the face of all kind of people. Measuring the Eye Lid level in the eye region. Interfacing the components. Testing and Implementation Detection of eye region and eye lid level are done by MAT LAB.
  • 18. Restricted Circulation | L&T Technology Services | © 2017 18PID No. Implementation and prototype / POC TG2019002028 Fig: Detection of face in the image Face Detection Feature Localization Face NormalizationFace Classification Still Image Recognition result
  • 19. Restricted Circulation | L&T Technology Services | © 2017 19PID No. Implementation and prototype / POC Image Acquistion Colour Compensation Face Detection Eye region detection & contour extraction Mouth region detection & contour extraction State Analysis TG2019002028
  • 20. Restricted Circulation | L&T Technology Services | © 2017 20PID No. Implementation and prototype / POC TG2019002028
  • 21. Restricted Circulation | L&T Technology Services | © 2017 21PID No. Validation / Testing / Analysis TG2019002028 The results of drowsiness detection of the driver will be validated by buzzer or HMI device. The input image which is captured by camera is being uploaded to the controller where the image is being processed to determine the face region and the eye region of the driver. The eye lid levels from the detected image will be analysed by Hough transform function. Based on the results, the buzzer or HMI devices set to go.
  • 22. Restricted Circulation | L&T Technology Services | © 2017 22PID No. Cost and benefits TG2019002028 ITEMS COST Rental Car or Car Simulator ₹ 35,000 * Camera ₹ 14,000 Raspberry Pi ₹ 4,000 Hard Disk ₹ 5,000 Buzzer or HMI ₹ 7,000 Infrared(IR) illuminator ₹ 500 Total ₹ 65,500 *The above cost is only for prototype model.
  • 23. Restricted Circulation | L&T Technology Services | © 2017 23PID No. Results and potential Business Impact TG2019002028 For proof of concept, a proto-type of drowsiness detection will be demonstrated in either car simulator or in a model car. In product level, the eye lid detection is acheived by Mat Lab simulation implemented in the raspberry pi module. At present in the market, this technology is not implied in the cars. The proposed product may increase the profit of L&T when it released in the market by L&T. When the proposed system will be designed and fabricated inside the car, it will become more compact and will be an additional unique feature to ADAS cars. This will provide potential business impact for L&T because it is like almost safety feature adding to ADAS.
  • 24. Restricted Circulation | L&T Technology Services | © 2017 24PID No. Conclusion TG2019002028 A proto-type model titled, Drowsiness state detection of driver using Eye Lid movement” is discussed in the challenge, “Determination of eye lid opening by driver using MATLAB -SIMULINK modelling technique”. The challenge/requirement in developing POC for the detection of various eyelid opening levels is determined and a warning will be given if the opening level is so much less when compared with the normal eye open level. The performance and accuracy of the module developed will be maintained as discussed. Further by using many HMI interfaces this project can be developed and accidents can be reduced.
  • 25. Restricted Circulation | L&T Technology Services | © 2017 25PID No. References TG2019002028 Elzohairy Y (2008) Fatal and injury fatigue-related crashes on ontario’s roads: a 5-year review. In: Working together to understand driver fatigue: report on symposium proceedings, February 2008 Dingus TA, Jahns SK, Horowitz AD, Knipling R (1998) Human factors design issues for crash avoidance systems. In: Barfield W, Dingus TA (eds) Human factors in intelligent transportation systems. Lawrence Associates, Mahwah, pp 55–93 Saito H, Ishiwaka T, Sakata M, Okabayashi S (1994) Applications of driver’s line of sight to automobiles—what can driver’s eye tell. In: Proceedings of vehicle navigation and information systems conference, Yokohama, Japan, pp 21–26 Ueno H, Kaneda M, Tsukino M (1994) Development of drowsiness detection system. In Proceedings of vehicle navigation and information systems conference, Yokohama, Japan, pp 15–20 Boverie S, Leqellec JM, Hirl A (1998) Intelligent systems for video monitoring of vehicle cockpit. In: International Congress and exposition ITS: advanced controls and vehicle navigation systems, pp 1–5
  • 26. Restricted Circulation | L&T Technology Services | © 2017 26PID No. Kaneda M et al (1994) Development of a drowsiness warning system. In: The 11th international conference on enhanced safety of vehicle, Munich Onken R (1994) Daisy, an adaptive knowledge-based driver monitoring and warning system. In: Proceedings of vehicle navigation and information systems conference, Yokohama, Japan, pp 3–10 Feraric J, Kopf M, Onken R (1992) Statistical versus neural bet approach for driver behaviour description and adaptive warning. The 11th European annual manual, pp 429–436 Ishii T, Hirose M, Iwata H (1987) Automatic recognition of driver’s facial expression by image analysis. J Soc Automot Eng Jap 41:1398–1403 Yammamoto K, Higuchi S (1992) Development of a drowsiness warning system. J Soc Automot Eng Jap 46:127–133 References TG2019002028
  • 27. Restricted Circulation | L&T Technology Services | © 2017 THANK YOU

Editor's Notes

  1. Title Text Font Calibri Body Bold, Font Size 34, Name and Designation Font Size 18