Chapter 1

INTRODUCTION

Real Time dangerous behaviours which are related to fatigue are in the form of eye closing, head
nodding or the brain activity. Hence we can either measure change in physiological signals, such as
brain waves, heart rate and eye blinking to monitor drowsiness or take into account physical changes
such as sagging posture, leaning of drivers head and open/closed state of eyes. The former
technique, while more accurate, is not realistic since highly sensitive electrodes would have to be
attached directly on the drivers body and hence which can be annoying and distracting to the driver.
In addition long time driving would result in perspiration on the sensors, diminishing their ability to
monitor accurately. The second technique is to measure physical changes (i.e. open/closed eyes to
detect fatigue) is well suited for real world driving 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
seconds 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.

1.1 Problem Statement

In the 1990s, driver fatigue has continued to be a major industry and public safety concern. The 1995
FHWA-sponsored Truck and Bus Safety Summit attended by over 200 national leaders in CMV and
highway safety, including a large contingent of drivers, identified driver fatigue as the top priority CMV
safety issue. Accordingly, the fatigue issue dominates current FHWA-sponsored human factors research on
CMV driving safety. Driver fatigue is a safety issue of special concern to CMV transportation. Under current
U.S. Federal hours-of-service (HOS) regulations, CMV drivers may drive up to 10 hours after a mandatory
8-hour off-duty period. In Canada, the maximum driving time is 13 hours. Many CMVs often run at night,
and drivers sometimes have irregular and unpredictable work schedules. Most of their mileage is compiled
during long trips on Interstate and other limited-access highways. Because of the CMVs’ high annual
mileage exposure (often 5-10 times that of passenger vehicles) and other factors, commercial drivers’ risk of
being involved in a fatigue-related crash is far greater than that of non-commercial drivers – even though
CMV drivers represent a relatively small proportion of all drivers involved in fatigue-related crashes. In
addition, many other crash causation factors, such as alcohol use, speeding, and other unsafe driving acts, are
generally less common in crashes involving commercial drivers. Thus, fatigue is a relatively larger concern
for these CMV drivers and their vehicles.

1
1.2 Objectives

Fatigue warning systems (FWS) have been proposed as specific countermeasures to reduce collisions
associated with driver fatigue. These devices employ a variety of techniques for detecting driver drowsiness
while operating a vehicle and signal a driver when critical drowsiness levels are reached. However, the
detection of driver fatigue using valid, unobtrusive, and objective measures remains a significant challenge.
Detection techniques may use lane departure, steering wheel activity, ocular or facial characteristics. Along
with this of course, Drivers have a duty not to exceed speed limits, exceed maximum work limits or breach
minimum rest requirements. Complementing this, entities within the chain of responsibility must take
reasonable steps to prevent driver fatigue or situations that lead to drivers breaching speed limits. It provides
extensive information on the alertness, driving performance, and physiological and subjective states drivers

1.3 Hardware Requirements

i. Ram: 1 GB

ii. Hard disk: 15 GB

iii. Webcam

1.4 Software Requirements

i. Python IDLE

2
 CHAPTER 2

LITERATURE SURVEY
Technological approaches for detecting and monitoring dangerous levels of driver drowsiness continue to
emerge and many are now in the development, validation testing, or early implementation stages. In this
section, some currently available drowsy driver monitoring devices, as well as technologies that will be
available in the near future for commercial transport

2.1 Attention Technology Inc.

Attention Technology Inc. has designed and developed the DD850 Driver Fatigue Monitor (DFM), the only
real-time, on-board drowsiness monitor that is currently being tested in an extensive field operational test.
The DFM is a video-based drowsiness detection system for measuring slow eyelid closure.

2.1.1 Advantages

1. Specifically, the DFM estimates PERCLOS, which is the proportion of time the eyes are closed 80% or
more over a specified time interval.

2. PERCLOS has been demonstrated in both driving and non-driving tasks to be a valid indicator of
drowsiness and performance degradation due to drowsiness. The high contrast between the pupils and the
rest of the face can significantly improve the eye tracking robustness and accuracy.

2.1.2 Disadvantages

1. The success of the bright pupil technique strongly depends on the brightness and size of the pupils, which
are often functions of face orientation, external illumination interference, and the distance of the subject
from the camera

2. For real-world, in-vehicle applications, sunlight can interfere with IR illumination, reflections from
eyeglasses can create confounding bright spots near the eyes, and sunglasses tend to disturb the IR light an
make the pupils appear very weak.

3. Thus, the DFM is intended for use in commercial operations involving nighttime driving.

2.2 Seeing Machines face LAB

Seeing Machines face LAB provides head and face tracking as well as eye, eyelid, and gaze tracking for
human subjects using a non-contact, video-based sensor

3
2.2.1 Advantages

1. FaceLAB has a flexible and mobile tracking system and a wide field of view that enables analysis of
naturalistic behavior, including head pose, gaze direction, and eyelid closure, in real time under real-world
conditions without the use of wires, magnets, or headgear. Thus, it is a tool that has great promise for
analyzing driver behavior in simulators and test vehicles.

2. It is not sensitive to sudden movement or obstruction, and it recovers immediately if a subject leaves the
field of view. The device reportedly works in bright sunlight or at night, with subjects close to the camera or
several feet away

2.3 LC Technologies, Inc.

LC Technologies, Inc. has developed an eye tracking technology that is both an eye operated computer for
control and communication and a device for monitoring and recording eye motion and related eye data. For
its use as a drowsy driver detection and warning system, the Eyegaze System can be housed in the vehicle
cab to warn and alert drivers when they are becoming drowsy and losing alertness on the road.

2.3.1 Advantages

The goal of the system is to monitor the driver’s eye point-of-regard, saccadic and fixation activity, and
percentage eyelid closure reliably, in real time, and under all anticipated driving conditions.

2.3.2 Disadvantages

In most cases, eye tracking works with eyeglasses and contact lenses since the calibration procedure
accounts for the refractive properties of the lenses. However, eyeglasses tilted significantly downward, hard
contact lenses, and sunglasses may cause problems for the device In addition, sunlight contains high levels
of infrared light and obscures the lighting from the devices LED, degrading the image of the eye

4
 CHAPTER 3

SYSTEM ANALYSIS AND DESIGN

3.1 Flowchart

Fig.1

Flowchart

5
3.2 Block Diagram

Fig. 2

Block Diagram

3.3 Algorithm

1. Camera input to our project

2. Face recognition .xml file also as an input to emgucv recognition engine

3. recognised face region + eye recg .xml as input to recg eng

4. Apply Hough circle transform to recognised eye region

5. If eyeball not detected for 10s then generate alarm

6. Repeat from step1

The Algorithm used here is very much fast as compared to PERCLOS earlier used by other hence the
Processing time of this system is less than half second hence it is quite fast and issues timely warning to the
driver. This system will detect a driver fatigue by processing of eye region. As shown in flow chart in Fig.1.
After image acquisition, face detection is the first stage of processing. Then symptoms of hypo-vigilance are
extracted from the eyes. If eyes are blinking normally no warning is issued but when the eyes are closed for
more than half second this system issues warning to the driver in form of alarm and vibration.

6
 CHAPTER 4

RESULTS
The whole detection mechanism for drowsiness is ported in a Linux environment. The proposed system
hence, is built on Ubuntu 13.04. The algorithm is implemented using the OpenCV library. According to the
proposed system, the live feed is first converted into frames, the average face and eye detection time.

Fig. 3

Execution of Project

The input frame is then laid across the face detection algorithm using the Haar Cascade Classifiers. After the
detection of the face, the eyes are tracked and identified. The algorithm is able to detect the eyes even in the
presence of glasses. Once the face is detected and the eyes are tracked, the drowsiness detection starts. The
states of eyes are checked for and accordingly the driver is prompted with an alert or warning. The results of
the same are illustrated below.

7
 Fig. 4

Open eyes

Fig. 5

Drowsiness Detected

8
 Fig. 6

Drowsiness detected with glasses

Drowsiness affects mental alertness, decreasing an individual’s ability to operate a vehicle safely and
increasing the risk of human error that could lead to fatalities and injuries. Furthermore, it has been shown to
slow reaction time, decreases awareness, and impairs judgment. Long hours behind the wheel in monotonous
driving environments make truck drivers particularly prone to drowsy-driving crashes successfully
addressing the issue of driver drowsiness in the commercial motor vehicle industry is a formidable and
multi-faceted challenge. Since a large number of road accidents occur due to the driver drowsiness, this
system will be helpful in preventing many accidents, and consequently save money and reduce personal
suffering. This system will monitor the driver’s eyes using a camera

9
 CHAPTER 5

CONCLUSION

The driver drowsiness detection aims to eradicate the problem of sleepiness among drivers
and if the driver sleeps then, the eye is detected and accordingly the alarm works. In the
future, we would add emotion detection, age detection and gender detection. The emotion
detection will be used to play the music as per the mood of the driver. Thus, the scope of the
project is wide and helps drivers across the world. OpenCV and machine learning has been
used to code the idea and thus the project is completed.

10
 CHAPTER 6

REFERENCES
1. Hu, Shuyan, and Gangtie Zheng. "Driver drowsiness detection with eyelid related parameters by
Support Vector Machine." Expert Systems with Applications 36.4 (2009): 7651-7658.4.
2. Sahayadhas, Arun, Kenneth Sundaraj, and Murugappan Murugappan. "Detecting driver drowsiness based on
sensors: a review." Sensors 12.12 (2012): 16937-16953.
3. Forsman, Pia M., et al. "Efficient driver drowsiness detection at moderate levels of drowsiness." Accident
Analysis & Prevention 50 (2013): 341-350.
4. Eskandarian, Azim, and Ali Mortazavi. "Evaluation of a smart algorithm for commercial vehicle driver
drowsiness detection." 2007 IEEE Intelligent Vehicles Symposium. IEEE, 2007.
5. Grace, Richard, et al. "A drowsy driver detection system for heavy vehicles." 17th DASC. AIAA/IEEE/SAE.
Digital Avionics Systems Conference. Proceedings (Cat. No. 98CH36267). Vol. 2. IEEE, 1998.

11