Impact of Image Processing in Saving The Human Life by Automating Traffi C Signals

HCTL Open Int. J.
of Technology Innovations and Research

HCTL Open IJTIR, Volume 3, May 2013
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
Impact of Image
Processing in Saving the
Human Life By
Automating Trafc
Signals
Manoj Prabhakar
and Manoj Kumar
Abstract
T
Time is of the essence when it comes to saving something as
valuable as the human life. In the modern congested cities of
today, the dierence between life and death could very well be
the few minutes of delay in getting appropriate medical attention.
Each second an ambulance spends waiting in the piled up trac
increases exponentially the threat to the patients life. This paper
explains about a novel Image Capturing System (ICS) based trac
routing approach to address the serious issue of saving human life
which otherwise would be lost during the transferral to a hospital
by means of an ambulance. The ICS will be used to trigger the
connected trac signal on recognizing an ambulance coming towards
manojkrishs@gmail.com
manojkumars.msec@gmail.com
Manoj Prabhakar and Manoj Kumar
Impact of Image Processing in Saving the Human Life By Automating Trac
Signals
Page 1 of 16
HCTL Open Int. J. of Technology Innovations and Research
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
it by means of changing the signal automatically to green in favor of
the ambulance. This in-turn will signicantly reduce the time spent
by them near the intersections thereby saving precious human lives
which otherwise would have been lost.
Keywords
Image Processing, Trigger, Ambulance, Human Life
Introduction
An image is nothing but the subset of signal. Generally a signal is used to
convey the information form one end to other end. These sort of signals can be
used in many ways. Electrical signals are used in television, radio, etc, which is
transmitted by electrical quantities. Here the digital processing is the process
of extracting information from the signals. Every signals will have certain
information which is to be transmitted to the other end.
The digital signal processing is mainly related representing and processing
of the numbers (sequence) and symbols. The signals have many characteristics
such as its shapes, time durations, amplitudes and etc. These signals can be
classied as continuous and discrete time signals based on sampling. There are
two types of signals, Analog and digital signals. If the signals are repeating
after some period, they are called periodic signals. Every signal can be xed by
Mathematical functions. The signals are classied into three types according to
its dimensions. They are 1D (One-Dimensional), 2D (Two-Dimensional), 3D
(Three-Dimensional).
The One Dimensional signals will be using time waveforms x(t) or f(t). Two
dimensional signals will be used two axis such as (x,y) 2D signals are the
function of two independent variables called as (x,y) and has been projected in
x,y plane. The 2D signals will be projecting the images and still photographs.
The Three dimensional signals will be plotted in (x,y,z) plane. It represents
the images in sequences and in dynamic manner, which in turn called as video
signals. Here, we are using the digital image processing to transmit signals
to trac signals and thereby triggering the Signal to green for ambulances.
This can be done by using the placing the motion camera in all trac signals,
which captures the video signals and when there in ambulance in the road, it
automatically changes the signal green according to the speed and time where
ambulance has been placed. Also we will be keeping signal transmitter in all
Signals
Page 2 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
ambulances, which emits the signals in particular frequencies to the receiver
that has been placed in trac signals. These signals will be unique for dierent
ambulances which consist of all the details of ambulances. The receiver that
has been placed in the trac signals will receive the signals transmitted by
ambulance. In this paper, we will be discussing about how the images will be
recognized and how the signals will be transmitted.
In order to provide the clear image we will be using smoothing lter and
sharpening lter which reduce the distortion and interference while capturing
the images and in order to provide enhancement for the images for better
accoutrement, basic morphological algorithms will be used and for pattern
recognition, clustering algorithm is used and for determining shortest path,
Djikistra shortest path algorithm will be implemented.
Helpful Hints
When the road is completely lled with trac, it is necessary to have natural
trac signal changes for ambulances that are in very critical in saving human
life. Here the motion camera that has been placed in trac signals will capture
the Three-Dimensional Images of vehicles in roads, and when the ambulance
is captured in camera, it automatically triggers they signals to green in the
distance where the ambulance has been viewed. In order to determine the side
of the ambulance the additional IC HT12E as Encoder, which will be placed in
ambulances and IC HT12D will be placed in all trac signals, which decodes
the signals.
The motion camera will be placed in the trac signals which captures the
3D images in x, y, z plane and determines the location of ambulance and
thereby trigger the trac signal. If there is more number of ambulances in
dierent directions, then we will be determining the shortest path algorithm
and for the ambulance that is present near will receive the green signal rst and
correspondingly. Similarly, in image capturing, the unique thing will be all the
ambulances will have name AMBULANCE in reverse manner such as ECNALUBMA,
this will be used as the primary image recognition pattern.
Motion Camera
The motion camera is the major element which captures the images of ambu-
lance and transmits the signals to trac signals which works on Integrated
circuits. These cameras mainly focuses on the parameters like swing angles,
Signals
Page 3 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
actual pan, zooming factor, tilt, and scaled focal length of the camera.
Let (X,Y,Z) be considered as a co-ordinate system of camera . Here the
Figure 1: The camera coordinate system, image coordinate system and perspective
imaging.
image plane will be lying perpendicular to that of Z-axis along with its cen-
ter which has been located at the point (0,0,f). Here, based on perspective
projection P = (X,Y,Z), and the 3D space is projected onto the point, where
p=(x,y) and the values of x and y be fX/z and fY/z receptively. Here we will
be detracting some of the motion parameters such as:
1. Pan angle a: rotation angle around the Y-axis,
2. Zoom factor s: ratio of the camera focal lengths between two image frames,
3. Tilt angle/3 rotation angle around the X-axis,
4. Translation vector t = (t
x
, t
y
, t
z
)T,
5. Swing angle r : rotation angle around the Z-axis
Smoothing Filter
A smoothing lter is mainly used to replace the each pixel values that are
present in input image with its neighbouring images. This in turn will eliminate
the pixel values that are not relevant to its surroundings. This smoothing
lter will be like other kernel lters, which considers the size and shape of its
Signals
Page 4 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
neighbourhood to calculate sampling.
The following image will demonstrate the dierence between the normal image
and smoothing image. We also will be using the Gaussian lter for the smooth-
ing the image. The Gaussian lter is the bell shaped hump will screen the high
spatial frequencies along with the noise and thereby produces the smoothing
eect.
The distortion in signal will be reduced by smoothing lter, which focuses
mainly on the primary image and its surrounding, eliminating the unnecessary
surroundings. The Gaussian lter ID is given as:
G(x) =
1
2
e
x
2
2
2
(1)
Where, is standard deviation of distribution in the Gaussian lter.
Figure 2: (a) Before smoothing (b) After smoothing
Sharpening lter
The sharpening lter is used to adjust the contrast of the image and also to
enhance the edges of objects. Generally, the sharpening lters (High-pass lters)
are allowed to pass and delete the low-frequency components. Generally, these
sharpening lters will eliminate the noise distortion and provides the proper
Signals
Page 5 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
visibility and image quality, when it is being captured by the camera. The
sharpening lters are generally classied as:
1. Derivative lter,
2. Laplace lter,
3. High Pass lter (HPF),
4. High Boost lter
Here, we are using the high boost lter to enhance the image further by using
low pass.
High boost = A original low pass
High boost = (A-1) original + (original low pass)
High boost = (A-1) original + high pass.
Figure 3: (a) Before sharpening (b) After sharpening
Avoid Image Blur during Image Capture
Three types of blur usually occurred in image processing are motion, Gaussian,
and compression blurs.
Motion blur maybe due to object movement when a camera shutter remains
open for an extended period of time and the object motion within this interval
is visible in a single snapshot. It can also be caused by camera movement.
Signals
Page 6 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
Gaussian blur is made by a soft lens to spread out the light on the focal
plane, rather than all going toward a spot. It produces a smoothing eect by
removing image details or noises.
Compression blur is triggered by the loss of high-frequency components in
JPEG compression.
The following image describes the above types of image blurs available while
capturing an image.
Let f(x
i
) denote the IQM score of an image under the degree of blur x
i
.
Figure 4: (a)Original image, (b)motion blur at orientation 45 degrees and magnitude
40, (c) Gaussian blur with a 17 x 17 window, (d) compression blur with
compression ratio of 1:160.
The IQMs used for measuring image blurs must satisfy the monotonically in-
Signals
Page 7 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
creasing or decreasing property. That is, if x
i+1
> x
i
, then f(x
i+1
) f(x
i
) > 0
for monotonically increasing or f(x
i+1
) f(x
i
) < 0 for monotonically decreasing
property. The sensitivity of IQMs is dened as the score of the aggregate
relative distance:
i
f(x
i+1
) f(x
i
)
f(x
i
)
(2)
Nine IQMs, which are grouped into three categories based on pixel distance,
correlation, and mean square error, are as follows,
Let F(j,k) denote the pixel value of row j and column k in a reference im-
age of size Mx N, and F(j,k) denote the pixel value in a testing image.
Category I: IQMs based on Pixel Distance
1. AD (Average Distance):
AD =
M
j=1
N
k=1
|F(j, k) F
(j, k)|/MN (3)

2. L2D (L2 Euclidean Distance):
L2D =
1
MN
_
_
M
j=1
N
k=1
(F(j, k) F
(j, k))
2
_
_
1
2
(4)
Category II: IQMs based on Correlation
3. SC (Structure Content):
SC =
M
j=1
N
k=1
F(j, k)
2
M
j=1
N
k=1
F
(j, k)
2
(5)
4. IF (Image Fidelity):
IF = 1
_
M
j=1
N
k=1
(F(j, k) F
(j, k))
2
M
j=1
N
k=1
F(j, k)
2
_
(6)
5. NK (N Cross-Correlation):
NK =
_
M
j=1
N
k=1
F(j, k)F
(j, k)
M
j=1
N
k=1
F(j, k)
2
_
(7)
Signals
Page 8 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
Category III: IQMs based on Mean Square Error
6. NMSE (Normal Mean Square Error)
NMSE =
_
M
j=1
N
k=1
(F(j, k) F
(j, k))
2
M
j=1
N
k=1
F(j, k)
2
_
(8)
7. LMSE (Least Mean Square Error)
LMSE =
_
M
j=1
N
k=1
(F(j, k) F
(j, k))
2
M
j=1
N
k=1
O(F(j, k))
2
_
(9)
8. PMSE (Peak Mean Square Error)
PMSE =
1
MN
M
j=1
N
k=1
_
(F(j, k) F
(j, k))
2
(max
j,k
[F(j, k)])
2
_
(10)
9. PSNR (Peak Signal to Noise Ratio)
PSNR = 20 log
10
_
_
255
(
M
j=1
N
k=1
(F(j, k) F
(j, k))
2
)
1
2
_
_
(11)
Pattern Recognition
In order to recognize the pattern of the ambulance in heavy trac, we will
be using the clustering algorithm, In particular two-pass mode clustering
algorithm. This clustering algorithm will require and process only the reg-
istered multi-spectral image, twice. Here, the pattern of ambulance will be
imparted in the device and such that whenever the motion camera nds the
pattern similar to that of recognized pattern, it will be recognized. In clustering
algorithm, there are two passes available. In rst path, the mean vectors of all
clusters will be generated and in the next pass, each every pixel will be assigned
to a cluster that represents a single type, so as to determine the pattern exactly.
The notations that will be used in this algorithm is given below:
B: It represents the total number of bands used. These numbers are the di-
mensionality in spectral space. Here we are using 3D spectral space. C
max
: It
Signals
Page 9 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
represents the maximum number of clusters, r(P,k): the distance between mean
vector of current, cluster (k) and gray value vector of pixel p. It is given as:
r(P, k) =
_
B
i=1
(MEAN
i
(k) P
i
)
2
_
1
2
(12)
Where, 1 k C
max
, MEAN denoted the mean value of cluster k in band
i, Pi denotes the gray value in band I of pixel p. R is the constant radius in
spectral space used to decide the mean vector of new cluster. If the value of R
is lesser then r, then new cluster will be generated. Also, d(k1,k2) represents
the dierence between mean vector of two dierent clusters k1 and k2.
d(k
1
, k
2
) =
_
B
i=1
((MEAN
i
(k
1
) (MEAN
i
(k
2
))
2
_
1
2
(13)
Where, 1 k1, k2 C
max
and k1 = k2, Here, D is the constant radius in
spectral space, which is used to determine whether two distinct clusters k1 and
k2 should be emerged or not. N is the constant that represents the total number
of pixels to be evaluated. n(k) is the total number accumulated in cluster k.
Pass 1: Clusters Mean Vector Establishment
Here, the gray value vector of rst pixel is placed as initial clusters mean of
cluster I. Then Mean is calculated as:
MEAN
i
(k)
new
=
MEAN
i
(k)
old
n(k) +P
i
n(k) + 1
(14)
If the above equation is used,then the values present in the equation n
total
(total number of pixels) and n(k) will be incremented by one. This process
will be repeated until the new image has been placed. If the value of K or N
is lesser than n total and is equal to C
max
, then the process, which has been
repeating will be terminated. The distance between the tow mean vectors will
be used to calculate the recognition pattern. The decision radius nally is
mainly dependent upon the condition to activate the clusters and to merge it
nally. If the value of d is lesser than or equal to decision radius, then two
clusters will be merged and also new mean vector will be determined.
MEAN
i
(k) =
MEAN
i
(k
1
) n(k
1
) +MEAN
i
(k
2
) n(k
2
)
n(k
1
) +n(k
2
)
(15)
Signals
Page 10 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
Where, 1k,k1,k2 C
max
and also k1 = k2. Now, the total number of pixels in
the new cluster n(k), will be sum of the n(k1) and n(k2). At last, the number
of clusters are built as the group of individual pixels and its mean vectors will
be determined in the second pass.
Pass 2: Pixel Classication
Pass 2 in mainly used to classify each and every pixel into one of the clusters
that has been built in pass 1. The minimum distance method will be adopted
here, where the clusters wil recognize the images that are present near and by
using the minimum distance method, the pixels with spectral features will be
merged together, so as to ensure the ecient reliability of the merged images.
The pixels will be recognized by the motion camera that has been placed in
trac signals and thereby, the images of ambulance will be clearly recognized
by these pass 2 merged image, with the image that has been present closer to
the camera will be identied rst.
Determine the Nearest Ambulance (Shortest path Algorithm)
The idea behind the shortest path algorithm (Dijkstras algorithm) is to identify
the nearest ambulance in the trac when there is a case of ambulances coming
from more than one side. Since roads come in varying lengths we want to work
on weighted graphs for this problem. A weighted graph is simply a graph where
each edge e is assigned a non-negative value called the weight, w(e), of the edge.
A path is a sequence of vertices p = (v1,...,vn) such that vi vi + 1. Set ei =
(vi,vi+1). The length of a path p is d(p) = &Sigma w(ei). For convenience we
will also write w (u,v) to denote the weight of the edge (u,v). The idea behind
Dijkstras algorithm is breadth-rst search (BFS). This type of search explores
vertices by spreading out as new vertices are found. In our system, we will be
using the algorithm that consists of previous hop-node.
RF Signal Transmitter
The signal generator and transmitter play a very important role here. In case
of heavy trac it is dicult to identify the ambulances presence. In such
scenarios, this helps to identify the ambulance as these signals are transmitted
at a particular frequency and a baud rate. This radio frequency (RF) transmis-
sion system employs Amplitude Shift Keying (ASK) with transmitter/receiver
(Tx/Rx) pair operating at 434 MHz. The transmitter module takes serial input
and transmits these signals through RF. The transmitted signals are received
by the receiver module placed away from the source of transmission. The RF
Signals
Page 11 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
Figure 5: Dijkstras Algorithm [5]
signal transmitter should be available in all the ambulances so that once the
ambulance is within the range of the receiver it will be able to transmit the
signal to the receiver.
RF Signal Receiver
The receiver will be available in the trac signals which is used to detect the
signal from the nearest transmitter (ambulance) based on the shortest path
algorithm. The receiver, upon receiving these signals, sends them to the decoder
IC (HT12D) through pin2. The serial data is received at the data pin (DIN,
pin14) of HT12D. The decoder then retrieves the original parallel format from
the received serial data. This data will be used to trigger the signal change (if
Signals
Page 12 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
Figure 6: Improved Algorithm
it is red to green).
Components used for Signal Transmission
HT12D Decoder
HT12D is a decoder integrated circuit that belongs to 2
12
series of decoders.
This series of decoders are mainly used for remote control system applications,
like burglar alarm, car door controller, security system etc. It is mainly provided
to interface RF and infrared circuits. They are paired with 2
12
series of encoders.
Signals
Page 13 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
Figure 7: (a) RF Signal Transmitter and (b) RF Signal Receiver
The chosen pair of encoder/decoder should have same number of addresses and
data format.
HT12E Encoder
HT12E is an encoder integrated circuit of 2
12
series of encoders. They are
paired with 2
12
series of decoders for use in remote control system applications.
It is mainly used in transceiving RF and infrared circuits. The chosen pair of
encoder/decoder should have same number of addresses and data format.
Figure 8: (a) HT12D Decoder and (b) HT12E Encoder
Circuit Diagram - RF Transmitter & Receiver
Signals
Page 14 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8
Figure 9: Circuit Diagram - RF Transmitter & Receiver
Impacts
Current Scenario
Now-a-days due to more luxurious living, more four wheelers have replaced
2-wheelers. Moreover, industrialization (tech-parks) and need for space have
caused more congestion. This in turn increases trac. Amidst all these frenzied
life, one forgets the importance of human life.
Signals
Page 15 of 16
e-ISSN: 2321-1814
ISBN (Print): 978-1-62776-443-8 References
After this work
With the implementation of this idea, more lives can be saved. Due to the
implementation of these signal generators in every ambulance and image pro-
cessing techniques, the ambulance would be able to reach the hospital on time
which in turn would save a million lives.
Conclusion
Thus this is just an idea of implementing signal generators in ambulances to
save thousands of serious lives. With further improvements in the technology
used as of now like installing GPS based locators, etc., the process can be made
even better.
References
[1] FRANK Y. SHIH, IMAGE PROCESSING AND PATTERN RECOGNITION -
Fundamentals and Techniques, A JOHN WILEY & SONS, INC. Pu-
bilication, 2010.
[2] STrobotix, Chandigarh labs and Chawla Radios, RF based Wireless
Remote.
[3] Yoshihiro Ikefuji, Sadakazu Murakami, Video Signal Generator
circuit and video image processing device using the same,
Patent Number 5311296, Rohm Co., Ltd., May, 1994.
[4] Yap-Peng Tan, Sanjeev R. Kulkarni, Peter J. Ramadge, A NEW METHOD
FOR CAMERA MOTION PARAMETER ESTIMATION.
[5] http://eoinbailey.com/blog/dijkstras-algorithm-illustrated-explanation
This article is an open access article distributed under the terms and con-
ditions of the Creative Commons Attribution 3.0 Unported License (http:
//creativecommons.org/licenses/by/3.0/).
c 2013 by the Authors. Licensed by HCTL Open, India.
Signals
Page 16 of 16

Impact of Image Processing in Saving The Human Life by Automating Traffi C Signals

Enviado por

Dados do documento

Título original

Direitos autorais

Formatos disponíveis

Compartilhar este documento

Compartilhar ou incorporar documento

Opções de compartilhamento

Você considera este documento útil?

Este conteúdo é inapropriado?

Direitos autorais:

Formatos disponíveis

Impact of Image Processing in Saving The Human Life by Automating Traffi C Signals

Enviado por

Direitos autorais:

Formatos disponíveis

HCTL Open Int. J.

of Technology Innovations and Research

and Manoj Kumar

(j, k)|/MN (3)

Você também pode gostar