01-10-2016, 11:30 AM
1457192918-etcsit10281.pdf (Size: 392.48 KB / Downloads: 23)
ABSTRACT
This paper describes a real-time online prototype driverfatigue
monitor. It uses remotely located charge-coupleddevice
cameras equipped with active infrared illuminators to
acquire video images of the driver. Various visual cues that
typically characterize the level of alertness of a person are
extracted in real time and systematically combined to infer the
fatigue level of the driver. The visual cues employed
characterize eyelid movement, gaze movement, head
movement, and facial expression. A probabilistic model is
developed to model human fatigue and to predict fatigue
based on the visual cues obtained. The simultaneous use of
multiple visual cues and their systematic combination yields a
much more robust and accurate fatigue characterization than
using a single visual cue. This system was validated under
real-life fatigue conditions with human subjects of different
ethnic backgrounds, genders, and ages; with/without glasses;
and under different illumination conditions. It was found to be
reasonably robust, reliable, and accurate in fatigue
characterization.
INTRODUCTION
The ever increasing numbers of traffic accidents all over the
world are due to diminished driver’s vigilance level. Drivers
with a diminished vigilance level suffer from a marked
decline in their perception; recognition and vehicle control
abilities & therefore pose a serious danger to their own lives
and the lives of the other people. For this reason, developing
systems that actively monitors the driver’s level of vigilance
and alerting the driver of any insecure driving condition is
essential for accident prevention. Many efforts have been
reported in the literature for developing an active safety
system for reducing the number of automobiles accidents due
to reduced vigilance. Drowsiness in drivers can be generally
divided into the following categories:
Sensing of physiological characteristics.
sensing of driver operation
Sensing of vehicle response.
Monitoring the response of driver.
Among these methods, the techniques based on human
physiological phenomena are the most accurate. This
technique is implemented in two ways:
Measuring changes in physiological signals, such as
brain waves, heart rate, and eye blinking.
And measuring physical changes such as sagging
posture, leaning of the driver’s head and the
open/closed states of the eyes.
The first technique, while most accurate, is not realistic, since
sensing electrodes would have to be attached directly on to the
driver’s body, and hence 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 well-suited for
real world driving conditions since it can be non-intrusive by
using video cameras to detect changes. Driver operation and
vehicle behavior can be implemented by monitoring the
steering wheel movement, accelerator or brake patterns,
vehicle speed, lateral acceleration, and lateral displacement.
These too are nonintrusive ways of detecting drowsiness, but
are limited to vehicle type and driver condition. The final
technique for detecting drowsiness is by monitoring the
response of the driver. This involves periodically requesting
the driver to send a response to the system to indicate
alertness. The problem with this technique is that it will
eventually become tiresome and annoying to the driver. The
propose system based on eyes closer count & yawning count
of the driver. By monitoring the eyes and mouth, it is believed
that the symptoms of driver fatigue can be detected early
enough to avoid a car accident. The eye blink frequency
increases beyond the normal rate in the fatigued state. In
addition, micro sleeps that are the short periods of sleep
lasting 3 to 4 seconds are the good indicator of the fatigued
state, but it is difficult to predict the driver fatigue accurately
or reliably based only on single driver behavior. Additionally,
the changes in a driver’s performance are more complicated
and not reliable so in this system second parameter is also
considered which a yawning count is. In order to detect
fatigue probability the facial expression parameters must be
extracted first.
2. CONCEPT
Sleep related accidents tend to be more severe, possibly
because of the higher speeds involved and because the driver
is unable to take any avoiding action, or even brake, prior to
the collision. Horne describes typical sleep related accidents
as ones where the driver runs off the road or collides with
another vehicle or an object, without any sign of hard braking
before the impact. In 2002, the National Highway Traffic
Safety Administration (NHTSA) estimated that 35 percent of all traffic deaths occurred in crashes in which at least one
driver or no occupant had a BAC(Blood Alcohol Content) of
0.08 percent or more and that any alcohol was present in 41
percent of all fatal crashes in 2002.Such statistics are
sometimes cited as proof that a third to half of all fatal crashes
are caused by "drunk driving" and that none of the crashes
that involve alcohol would occur if the alcohol were not
present. But this is incorrect and misleading because alcohol
is only one of several factors that contribute to crashes
involving drinking drivers. Furthermore, some fatally injured
people in alcohol-related crashes are pedestrians with positive
BACs, and these fatalities still would occur even if every
driver were sober. Distracted driving is a top danger behind
the wheel. In fact, about eight out of 10 crashes involve some
sort of driver inattention within three seconds of that crash.
We've all seen it and likely even done it, driving distracted
includes anything from talking on the phone, to messing with
your music, to attending to your children or even pets. All of
these actions can lead to serious consequences. Martha Meade
with AAA Mid-Atlantic says, "People are dying because of a
simple missed phone call, a dropped toy or some other event
that is completely not important." Possible techniques for
detecting drowsiness in drivers can be generally divided into
the following categories: sensing of physiological
characteristics, sensing of driver operation, sensing of vehicle
response, monitoring the response of driver:
2.1 Monitoring Physiological
Characteristics:
Among these methods, the techniques that are best, based on
accuracy are the ones based on human physiological
phenomena. This technique is implemented in two ways:
measuring changes in physiological signals, such as brain
waves, heart rate, and eye blinking; and measuring physical
changes such as sagging posture, leaning of the driver’s head
and the open/closed states of the eyes. The first technique,
while most accurate, is not realistic, since sensing electrodes
would have to be attached directly onto the driver’s body, and
hence 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 well suited for real world driving conditions since
it can be non-intrusive by using optical sensors of video
cameras to detect changes.
2.2 Other Methods:
Driver operation and vehicle behaviour can be implemented
by monitoring the steering wheel movement, accelerator or
brake patterns, vehicle speed, lateral acceleration, and lateral
displacement. These too are non-intrusive ways of detecting
drowsiness, but are limited to vehicle type and driver
conditions. The final technique for detecting drowsiness is by
monitoring the response of the driver. This involves
periodically requesting the driver to send a response to the
system to indicate alertness. The problem with this technique
is that it will eventually become tiresome and annoying to the
driver.
3. EYE BLINK DETECTION
It is necessary in our working to find the blinking of eye,
since it is used to drive the device and to operate events. So
blink detection has to be done, for which we can avail readily