Drowsiness Detection

ROBUST HEAD TRACKING
BASED ON MULTIPLE CUES

FUSION IN THE KERNEL-
BAYESIAN FRAMEWORKS
OBJECTIVE
The main objective of the project is to ROBUST
HEAD TRACKING BASED ON MULTIPLE
CUES FUSION IN THE KERNEL-BAYESIAN
FRAMEWORKS.
EXISTING METHOD
In the existing method we can detect the visual
information by using sensors and after detecting it
rings buzzer to indicate that driver is not paying
attention on driving and after buzzer rings driver
will come to normal position and he will
concentrate on driving.

DISADVANTAGES OF EXISTING
SYSTEM:

In the existing method the main disadvantage is we
are detecting eyes by using sensors but we are not
identifying exactly weather the driver paying
attention on driving or not.

PROPOSED METHOD
In the proposed method the on line detection of drowsiness using brain
and visual information is to monitor the driver attentiveness in cars.
This project is to monitor the drivers eye movement, IRIS detection, eye
lids and head detection.
Our Embedded project is to design and develop a low cost feature which is
based on embedded platform for finding the driver drowsiness.
Specifically, our system includes a webcam placed on the steering column
which is capable to capture all the eye movements of the Driver to find out
whether he is sleeping or not.
If the driver is not paying attention on the road ahead trying to sleep, the
system will warn the driver by giving the warning sounds in the form of
buzzer.
Our Embedded System uses ARM micro controller has a feature of image
processing technique. Image processing is any form of signal processing
for which the input is an image, such as a photograph or video frame; the
output of image processing may be either an image or a set of
characteristics or parameters related to the image.

BLOCK DIAGRAM
ARM
ARCHITECTURE
REGULATED POWER
SUPPLY
USB HOST
WEBCAM
BUZZER
LINUX OS
APPLICATION
FRAME WORK
IMPLEMENTTION
For implementing this project we are using Linux, Qt
for embedded Linux and open CV library.
LINUX OPERATING SYSTEM
The Linux open source operating system, or
Linux OS, is a freely distributable, cross-
platform operating system based on Unix that
can be installed on PCs, laptops, net books,
mobile and tablet devices, video game consoles,
servers, supercomputers and more.

Qt for Embedded Linux
Qt for Embedded Linux is a C++ framework for
GUI and application development for embedded
devices.
It runs on a variety of processors, usually with
Embedded Linux.
Qt for Embedded Linux provides the standard Qt
API for embedded devices with a lightweight
window system.

OPEN CV
Open CV is an open source computer vision
library originally developed by Intel.
It is free for commercial and research use under
a BSD (Berkeley Software Distribution) license.
The library is cross-platform, and runs on Linux,
Windows and Mac OS X.
It focuses mainly towards real-time image
processing, as such, if it finds Intel's Integrated
Performance Primitives on the system, it will use
these commercial optimized routines to accelerate
itself.

Working Principle
In this section, we are giving the complete description on the
proposed system architecture. Here we are using Raspberry Pi
board as our platform. It has an ARM-11 SOC with integrated
peripherals like USB, Ethernet and serial etc.
On this board we are installing Linux operating system with
necessary drivers for all peripheral devices and user level
software stack which includes a light weight GUI based on
XServer, V4L2 API for interacting with video devices like
cameras, TCP/IP stack to communicate with network devices
and some standard system libraries for system level general
IO operations.
The Raspberry Pi board equipped with the above software
stack is connected to the outside network and a camera is
connected to the Raspberry Pi through USB bus. On the other
side we have to host a web server with cloud facility.

Contd
The system uses USB webcam which is places at fore
head of visually impaired person and is connected to
Raspberry PI board through USB device.
After connecting all the devices power up the device.
When the device starts booting from flash, it first loads
the linux to the device and initializes all the drivers and
the core kernel.
After initialization of the kernel it first checks weather all
the devices are working properly or not.
After that it loads the file system and starts the startup
scripts for running necessary processes and daemons.
Finally it starts the main application.
Contd
When our application starts running it first check all the
devices and resources which it needs are available or not.
After that it checks the connection with the devices and gives
control to the user. The GUI for the user has the following
options.
An optional label for displaying the image taken from the
camera.
A status box for representing whether drowsiness is detected
or not.
Proposed scheme uses visual features such as eye index (EI),
pupil activity (PA), and HP to extract critical information on
non alertness of a vehicle driver.
EI determines if the eye is open, half closed, or closed from
the ratio of pupil height and eye height. PA measures the rate
of deviation of the pupil center from the eye center over a time
period.

Contd
Our Embedded project is to design and develop a low
cost feature which is based on embedded platform
for finding the driver drowsiness.
Specifically, our system includes a webcam placed on
the steering column which is capable to capture the
eye movements.
If the driver is not paying attention on the road
ahead and a dangerous situation is detected, the
system will warn the driver by giving the warning
sounds through buzzer.
CONCLUSION
The project ROBUST HEAD TRACKING BASED ON
MULTIPLE CUES FUSION IN THE KERNEL-BAYESIAN
FRAMEWORKS has been successfully designed and
tested.
It has been developed by integrating features of all
the hardware components and software used.
Presence of every module has been reasoned out and
placed carefully thus contributing to the best
working of the unit.
Secondly, using highly advanced Raspberry pi board
and with the help of growing technology the project
has been successfully implemented.

APLLICATION LANGUAGE: C / C++

ADVANTAGES:
It avoids the accidents while driving.
Automatic monitoring system.
It avoids potential human errors.

APPLICATIONS:
It is used to give warning sounds for driver
drowsiness while driving.

REFERENCE:
Datasheets and the user manuals of ARM controller.
Beginning of Linux programming by Neil Matthew,
Richard Stones.

Drowsiness Detection

Uploaded by

Copyright:

Available Formats

Drowsiness Detection

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Drowsiness Detection

Uploaded by

Copyright:

Available Formats

ROBUST HEAD TRACKING

BASED ON MULTIPLE CUES

You might also like