Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
Abstract— A person when he or she does not have a proper by drowsiness because the driver believes that taking a rest
rest especially a driver, tends to fall asleep causing a traffic for a few seconds, closing his eyes, it can cause to losing the
accident. It is why the present work wants to realize a system control of the vehicle [4]. For this reason, in the present
that can detect the drowsiness of the driver, in order to reduce investigation, the designs of a system able to detect the
traffic accidents. For that system, it will take the processing of
images through a camera which will focus on the driver. In drowsiness of the driver in order to be alerted are presented.
that, it is going to analyze the changes that happen in the face Also, drowsiness detection of the driver's approach driver is
and then will be processed through a program in order to confronted with image processing to recognize drowsiness
detect drowsiness to send an alert to the driver. patterns.
Keywords— Drowsiness, system, processing of images, face. In section II, the development of the objectives. Then, in
I. INTRODUCTION section III presents the results according to the objectives. In
section IV, a discussion about the results is shown and,
The human has a fundamental need called sleep because
finally, in section V, which exposes the conclusions.
with adequate rest, helps to maintain efficient operation of
the capacities that realize a person. However, when this II. METHODOLOGY
activity is interrupted by several factors, especially in a
The development of the research is following the next
driver, it deteriorates the psychomotor and cognitive
functions such as reaction time, the capacity of surveillance, objectives below:
judgment, and attention. A. The causes of driver drowsiness
When the driver does not have adequate rest, the driver • Sleep less than 8 hours: According to a study
will try to sleep while driving and this is the main sign of carried out in the final bus station of Huancayo to
drowsiness. In most cases, the driver does not pay attention, 100 interprovincial bus drivers, it states that in the
and then the yawns come, the attempt to close the eyes every 24 hours prior to the survey, 47% of the drivers had
moment and the movement of the head from side to side [1]. slept six hours or less [5]. This sample, the driver
It has as a consequence a traffic accident, which is an does not obey the eight hours appropriated for the
unfortunate event for the driver of the vehicle, as well as for quality of sleep in order to affect the health. For
the pedestrian. example, the person gets sick every moment,
Currently, there are studies for the creation of a decrease in the mood and quick reaction to avoid
drowsiness detection system, which extracts the essential some inappropriate event.
characteristics of drowsiness of the driver to determine the
level of drowsiness. In these systems, which are controlling In addition, in [6] developed a study on the number of
the state of drowsiness of the driver through a webcam with hours that the driver sleeps in a formal and informal
night vision to track the driver in real time and when business. This study focuses on day and night and shows in
drowsiness is detected, the system will send a warning [2]. tables 1 and 2.
The objective of these systems is to improve the safety of
people with the use of detection and alarm to avoid
accidents caused by drowsiness of the driver and which are
harmful to the users of the route [3].
In Peru, according to the Instituto Nacional de Estadística e
Informática shows that 0.6% of traffic accidents are caused
• Detection: At this stage, we will proceed with the Fig. 11: Image processing with close eyes
identification of drowsiness patterns. To process the
patterns will begin with the isolation of the section of
interest as the eyes. Then, the process of extracting • Alarm: Finally, after detection, the system will emit an
characteristics begins, which analyzes the moment of audible alarm to warn the driver to have drowsiness. The
closing the eyes and the distance from the opening of the alarm varies according to the pattern that has been detected
eyes. in relation to the sensitivity level. So the driver does not get
As shown in Figure 10, the programming takes 3 frames where used to a repetitive tone and ignores the warning.
the first one will capture the eyes of the driver, in the second The system consists of the camera, which acquires the
frame, it places the eyes and finally, in the third frame the image. The camera used belongs to the brand Micronics
program analyzes that the eye is opened by a green circle. with the model W360 MIC and consists of high resolution
with great clarity and is connected via USB to the laptop.
The use of the laptop will proceed with image processing
and driver drowsiness detection using MATLAB software.
Finally, the alarm is integrated into the software. The system
is in figure 12.
contador =0;
while true
vid=snapshot(cam); %
vid = rgb2gray(vid);
img = flip(vid, 2); %
floor(r+r/2)], 'ObjectPolarity','dark',
bbox = step(detector1, img); 'Sensitivity', 0.93); % Hough transform
[M,I] = sort(radii,
if ~ isempty(bbox) 'descend');
biggest_box=1;
for i=1:rank(bbox) %find the eyesPositions = centers;
biggest face
if
bbox(i,3)>bbox(biggest_box,3) subplot(3,2,2),subimage(eyesImage); hold
biggest_box=i; on;
end
end viscircles(centers,
faceImage = radii,'EdgeColor','g');
imcrop(img,bbox(biggest_box,:)); % stop %% count
the face
bboxeyes = step(detector1,
faceImage); % eyes located
cent= numel(eyesPositions);
subplot(3,2,1),subimage(img);
hold on; % showing if cent ==0 ;
contador= contador+1;
disp('hay parpadeo')
for i=1:size(bbox,1) % focus
subplot(3,2,4);
the face subimage(noParapadeo);
rectangle('position', else cent==1; contador
bbox(i, :), 'lineWidth', 2, 'edgeColor', =contador; disp('no hay
'y'); parpadeo');
end subplot(3,2,4);
subimage(parpadeo);
subplot(3,2,3),subimage(faceImage);
end
if ~ isempty(bboxeyes) %check if contador >= 5;
it eyepair is available disp('Tienes
somnolencia');
biggest_box_eyes=1; end
for i=1:rank(bboxeyes) %find
the biggest eyepair end
if
bboxeyes(i,3)>bboxeyes(biggest_box_eyes,
3) end
biggest_box_eyes=i;
end end
end set(gca,'XtickLabel',[],'YtickLabel',[]) ;
Oleh :
Panji Budi Satria (E41160482)
Frekuensi berkedip pada seseorang dengan tidur sekitar 21 berkedip per menit
dan dalam kondisi normal, orang tersebut memiliki 15 berkedip per menit.
2. Pembukaan Mata
Dan untuk perhitungan faktor ini PERCLOS digunakan, untuk
menentukan persentase penutupan kelopak mata. Rumus matematika berikut
ini disajikan dalam persamaan 2 digunakan, di mana t1 ke t4 adalah waktu di
mana pembukaan mata akan terbatas untuk sepenuhnya terbuka dari
penutupan.