(NANOTECHNOLOGY)
PRESENTED BY
G.PANNERSELVAM
P.PRASAD
111 YR ECE
e- Mail address:
pannerwelcome@yahoo.com
shivpalprasad@yahoo.co.in
ABSTRACT
This paper proposes a method for detecting frontal pedestrian crossings from
image data obtained with a single camera as a travel aid for the visually challenged. This
would be mounted on a pair of glasses, will be capable of detecting the existence and
location of a pedestrian crossing, to measure the width of the road, and to detect the color
of the traffic lights. The process of detecting a crossing is a pre-process followed by the
process for detecting the state of the traffic lights. It is important for the visually
challenged to know whether or not a frontal area is a crossing. The existence of a
crossing is detected in two steps. In the first step, edge detection and pattern detection are
employed to identify the crossing. In the second step, the existence of a crossing is
detected by checking the periodicity of white lines on the road using projective
invariants. Then the traffic light detector is used to check the pedestrian light and the time
display. The calculated time is then compared with the average time needed for a blind
person to cross. The observations are relayed through voice signals using the voice vision
technology. Thus, this effective technology aids mobility for the visually impaired
throughout the globe.
INDEX
Introduction
An overview of our Electronic Eye
Functioning of the system
Image Analyzer
Calculation of width of road and time required to cross it
Traffic light detector
Timing unit
Voice speech system
Functional block
Conclusion
INTRODUCTION a curb or crosswalk and frequently fail in
areas that have many tall buildings and
Blindness is the high traffic. None of these devices are
most feared of all human ailments. able to specifically identify a crosswalk,
CROSSING busy roads can be a nor do they have the potential for
challenge for people with good vision. figuring out the state of the traffic
For blind people, it is a perilous activity. signals.
Our electronic eye aims at helping
An effective
millions of blind and visually impaired
navigation system would improve the
people lead more independent lives.
mobility of millions of blind people all
The electronic eye over the world. Our new “eye” will
can be adapted to help the blind or allow blind people to cross busy roads
visually impaired get around without a in total safety for the first time. Our
walking stick or seeing-eye dog. Canes “electronic eye”, which would be
and other travel aids with sonar or lasers mounted on a pair of glasses, will be
can alert the user to approaching objects. capable of detecting the existence and
Global Positioning Systems can tell location of a pedestrian crossing, and at
what streets, restaurants, parks and other the same time measure the width of the
landmarks the user is passing. Devices road to the nearest step and detect the
like these are very good at giving color of the traffic lights.
locations and directions. But the
limitations of G.P.S. technology mean
that they cannot pin down the location of
AN OVERVIEW OF OUR ELECTRONIC EYE
A camera to
capture the image
of crossroads and
traffic signals
A voice speech
generator - used to
instruct the user
1
TRAFFIC VOICE TIMING
2
LIGHT SPEECH3
DETECTOR GENERATOR UNIT
1 2 3
TO USERS
EAR
1 – Tells the user whether any cross road invariant” which takes the distance
is present
between the white lines and a set of
2 - Tells the user whether the traffic
signal is favorable or not
linear points on the edges of the
3 – Tells the user the time taken to cross
white lines. This gives an accurate way
the road.
of detecting whether crossing is present
The style of crosswalks
in a given image or not.
commonly used in India are known as
The length of a pedestrian
zebra crossings and they feature a series
crossing is measured by projective
of thick white bands that run in the same
geometry. The camera makes an image
direction as the vehicle traffic.
of the white lines painted on the road,
To detect the presence of a zebra
and then the actual distances are
crossing we use the “projective
determined using the properties of for symmetrical shapes and compares
geometric shapes as seen in the image. them to a
The traffic light detector checks images
list of road signs. If the pedestrian light High-level scene interpretation
is ON, the voice speech system instructs applied to the processed images will
the user to cross the road. produce a symbolic description of the
Timer unit calculates the average scene. The symbolic description is then
time required by the visually challenged converted into verbal instructions
person to cross the road and ‘tells’ it to appropriate to the needs of the user by
the user via the voice speech system. using voice speech software
.
Calculation of the width of the road is based on the concept of projection invariants. This
requires us to define the term Cross Ratio. L1
P4 L2
P3
P2
L3
P1
L4
The cross ratio can defined for the four collinear points as,
τ (P1, P2, P3, P4) = (P1P3/P2P3)/ (P1P4/P2P4)
Where P1P2 is the distance P1 to P2. The cross ratio of the four lines is given by,
τ (L1, L2, L3, L4) = (sinθ /sinθ
13 )/ (sinθ
23 /sinθ
14 )
24
L2
P1
L3
P2
P3 L4
P4
In the above figure, lines are constructed
from the collinear points and in the
Here (λ ,µ ) are the coordinates of A in
adjacent figure a line is formed by
the 2D linear subspace spanned by the
joining the points in the lines L1, L2, L3,
coordinate vectors M and N. N is
L4.
represented by (0, 1) and serves as the
A useful fact is that the cross-
``origin'' and M is represented by (1, 0)
ratio of the original four points is equal
and serves as the ``point at infinity''.
to the cross-ratio of the constructed
For an arbitrary point (λ ,µ ) ≠ (1,0)
lines.
we can rescale (λ ,µ ) to µ =1 and
To detect the presence of a zebra
represent A by its ``affine coordinates'',
crossing we use the “projective
invariant” which takes the distance (λ , 1) or just λ for short. Since we
between the white lines and a set of have mapped M to infinity, this is just
linear points on the edges of the white linear distance along the line from N.
lines. The system effectively draws a The time required to cross the road is
virtual line out into the road. If a calculated based on an assumption that
crosswalk is present, the edges of the the user covers a distance of one foot in
painted white lines will form a a minute on an average. So, the time
predictable series of points along the required to cover the calculated distance
Let M and N be two distinct points of Generally, the time taken, T, to cross the
the projective space. Here we take points road can be found out by
PEDESTRIAN LIGHT
DETECTION
TIMER UNIT
CAPTURE IMAGE
ANALYSER
THE IMAGE
ANALYSE
THE
IMAGE
IS
YES THERE ANY NO
CROSS ROADS
CALCULATE
THE WIDTH
OF THE ROAD
IS THE TRAFFIC
LIGHT NO INFORM THE LIGHT
YES FAVOURABLE? USER TO WAIT DETECTOR
CALCULATE
THE TIME
TAKEN TO IDENTIFY THE TIME
CROSS THE LEFT IN THE
ROAD (A)
TRAFFIC SIGNAL (B)
YES IF NO
A<B
TIMER
INFORM THE INFORM THE UNIT
USER TO CROSS USER TO
THE ROAD WAIT
STOP
CONCLUSION Blind pedestrians in the greatest
danger are those who must cross wide,
The development of
busy roads. This system along with the
mobility aids for the visually
available low technology aids can
impaired is a challenging task
relieve the visually challenged of being
that has many potential
dependent on others and lead normal
solutions. A sophisticated mechanism
lives. This effective navigation system
designed to enhance the mobility of the
would improve the mobility of millions
blind is intended to help people who
of blind people all over the world.
cannot recover their eyesight by normal
medical procedures.