The document outlines a project focused on a driver safety system that detects eye blinks to assess the driver's status and control the vehicle accordingly. Using Matlab and a microcontroller, the prototype captures live images of the driver's eyes to implement algorithms for image segmentation and recognition. Future enhancements might include anti-drowsiness alarms and better interfacing with hardware, making the system efficient for real-time applications.

1. Stark Foundation
by

2. OBJECTIVE
• Nowadays the driver safety in the car is one of the most wanted system to avoid
accidents. Our objective of the project is to ensure the safety system. For
enhancing the safety, we are detecting the eye blinks of the driver and estimating
the driver status and control the car accordingly.

3. INTRODUCTION:
• Aim of this project is implementing the system as a prototype by capturing the live images of the
eyes and fed them in to the Microcontroller in which the MATLAB software is used to process the
video and convert it in to frames and process it accordingly. Some customized algorithms are
coded in MATLAB for image segmentation of eyes from the entire image and image recognition of
the eyes and face position.
• On the whole, by sensing the eye blinks we can decide if the eye blinks are more than the driver is
very sleepy, Drinking and it will automatically turn off the vehicle, if the driver is showing the left
eye ball position than the left indicator of the car is turned on and so on.

5. MATLAB WITH
MICROCONTRILLER
16FXXX
Image Processor Camera
E C U
Arduino Hardware Power Supply

6. METHODOLOGY:
• The eye blinks of the driver and estimating the driver status and control the car
accordingly. We are implementing the system as a prototype by capturing the live
images of the eyes and fed them in to the Microcontroller in which the MATLAB
software is used to process the video and convert it in to frames and process it
accordingly. Some customized algorithms are coded in MATLAB for image
segmentation of eyes from the entire image and image recognition of the eyes and
face position. On the whole, by sensing the eye blinks we can decide if the eye
blinks are more than the driver is very sleepy, Drinking and it will automatically
turn off the vehicle, if the driver is showing the left eye ball position than the left
indicator of the car is turned on and so on.
Y
-
-
Z
-
-
-

10. Future’s
 Anti-drowsiness Alarm
 Make Easy drive
 Drink and Drive production
 Medical accent
 Directly interface to any Hardware using Arduino
 Low cost
 High Security
 This program can use for Aircraft Also

11. Camera

12. Image Captured by Camera

13. Programming Environment (soft-&Hardware)
 For test and first implementations Matlad was used. It is not as fast as C code id ,
but not fast enough for real time experiences. Another Avanade of Matlab on
Windows machines is the possibility to simple access webcams with the image
acquisition . On the hardware side image processor Logitech quickcam pro model
we used .

14. Image Processing
 A lot of way can be developed to find pupils in the given area surrounding the eyes.
It can also be done using hue or saturation, which leads controlled conditions given
to good results , but it highly depends on the current light situation.
 Thus, another way is used to find the pupils. A picture of the pupil runs over the
current picture area and tries to find the place with the highest accordance. Different
pupils where used for testing and the best result were gained by pupils directly from
the tester, which was not really surprising. Obtaining them is not that simple that
simple thought. We name this algorithm is called Eagle Eye Safety. Which requires
too much calculating time to be used in real time environment's, but is fact enough
for getting pupils

15. o Microchip's 16-bit, PIC24 MCUs and dsPIC® Digital Signal Controllers provide designers
with an easy upgrade path from 8-bit
PIC® microcontrollers and a cost effective option to 32-bit MCUs. The broad product line
includes everything from eXtreme Low Power microcontrollers to high performance digital
signal controllers. With single cycle execution, deterministic interrupt response, zero
overhead looping, and fast DMA, the dsPIC family also adds a single cycle 16x16 MAC and
40-bit accumulators, ideal for math intensive applications like motor control and digital
power.

16. Arduino hardware
 MATLAB Support Package for Arduino hardware enables you to use
MATLAB to communicate with the Arduino® board over a USB cable. This
package is based on a server program running on the board, which listens to
commands arriving via serial port, executes the commands, and, if needed,
returns a result. This approach helps you

17. E C U