Scribd
Upload
543 views

Driver Fatigue Detection Using MATLAB

The document describes a system to detect driver fatigue using image processing with MATLAB and a PIC controller. A camera captures video of the driver and images are used for face detection and eye tracking algorithms in MATLAB. If fatigue is detected, MATLAB sends a signal to the PIC controller via serial communication. The controller then slows a DC motor, turns on warning lights and a buzzer to alert the driver. The system aims to increase road safety by reducing accidents caused by drowsy driving.

Uploaded by

Yogesh Gowda
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
543 views

Driver Fatigue Detection Using MATLAB

The document describes a system to detect driver fatigue using image processing with MATLAB and a PIC controller. A camera captures video of the driver and images are used for face detection and eye tracking algorithms in MATLAB. If fatigue is detected, MATLAB sends a signal to the PIC controller via serial communication. The controller then slows a DC motor, turns on warning lights and a buzzer to alert the driver. The system aims to increase road safety by reducing accidents caused by drowsy driving.

Uploaded by

Yogesh Gowda
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

Driver Fatigue Detection using MATLAB & PIC Controller

Aim:
Detect driver fatigue using MATLAB and send signal to PIC controller based vehicle

Abstract:
In this paper, a system to detect the driver fatigue and send signal to controller is presented. Video capturedusing a camera located in a car in front of the driver. These imagesare used for tracking as input of the proposed method. In first step color space for drivers face detection and crop the face from background will be used. In the next step, the area of the eyes andcrop image from this region will be estimated. Then top and bottom coordinates of theeyes are located using retrench the face pixels from this area andcanny operator for edge detection. In the last step we count thenumber of white and black pixels and compare the distance betweenthese coordinates for recognition of the drivers fatigue and send the signal to controller through serial communication for further process.

Existing System:
Driver fatigue is one of the main ingredients in accidentsand criminal casualty in roads. Recently, for these reason thereare many researches in this subject for increasing the safety in vehicles. Generally driver drowsiness is main factor in25percent accidents and 60 percent in accidents that they redound to death [1]. So designing Intelligent DriverMonitoring System that can recognize driver fatigue is soimportant. In the past two decades many researchers have begun to paygreat attention to the driver safety problem. We can dividemost of used techniques for driver fatigue detection to threegeneric sections. First one consist the systems that investigatephysiological information of drivers.This method focuses on measuring physiological changesof drivers. It can accurately, validly, and objectively todetermine fatigue and sleep of the drivers.

The second method consist of systems that theyuse vehicles behavioral for detect driver drowsiness. Such assteering wheel movements, drivers grip force on the steeringwheel, speed, acceleration, lateral position, turning angle,changing course, braking and gear changing,etc [2]. The last one use image processing for detecting driversphysical changes during fatigue. We can observe thesephysical changes in facial features. Visual behaviors likeeyelid movement, yawing, gazing, nodding and open or closedeyes.

Proposed System:

GREEN LED

RED LED

LEDLED

LEDLED

Fatigue Detection Algorithm in MATLAB

IC MAX232 MAX232

PIC 18FXX Controller

DC Motor

Buzzer

Figure 1: Block diagram of proposed system

A system to detect the driver fatigue and send signal to controller is presented in block diagram shown above. Video capturedusing a camera located in a car in front of the driver. These imagesare used for tracking as input of the proposed method. In first step color space for drivers face detection and crop the face from background will be used. In the next step, the area of the eyes andcrop image from this region will be estimated. Then top and bottom coordinates

of theeyes are located using retrench the face pixels from this area andcanny operator for edge detection. In the last step we count thenumber of white and black pixels and compare the distance betweenthese coordinates for recognition of the drivers fatigue and send the signal to controller through serial communication for further process.

Methodology:
Face Detection Algorithm: Read the captured video of the driver Extract frames from the video Detect the face from each frame using skin detection technique based on YCbCr /
RGB facial components

Figure 2: Detected face

Estimate the eye and eye region the from face

Figure 3: Eye region cropped

Detect the fatigue of driver based on eye ball tracking / eye lid and eye brow distance Method

Figure 4: (a) Eye opened detected,

(b) Eye closed detected

Send signal to the controller based on fatigue detection result

Hardware flow: By default motor and Green LED will be in ON state to indicate the system is running Receives the signal from algorithm through serial communication Once the controller the signal of fatigue, it sends signal to DC motor, LED and Buzzer DC motor pulse is reduced gradually to slow down speed and stop Green LED stops glowing and RED LED glows Buzzer get ON

References:
[1] Bergasa L. M., Nuevo J. u., Sotelo M. A., Barea R., and Lopez VisualMonitoring of Driver Inattention, Studies in Computational Intelligence(SCI). (2008). [2] Xiao Fan a,b,*, Yanfeng Sun a, Baocai Yin a, XiumingGuoGaborbaseddynamic representation for human fatigue monitoring in facialimage sequences Pattern Recognition Letters 31 (2010) 234243

You might also like