1. control of real time traffic with the help of image processing

Prof Mrs Priti Tyagi, Mr Sandeep Oberoi, Mr Satish Sonawane, Tejal Rane and Mahip Shrawagi 1
IRET Transaction on Image Processing (ITIP) Vol. 1, Issue. 1, April-2014.
Control of Real Time Traffic with the Help of
Image Processing
Prof Mrs Priti Tyagi, Mr Sandeep Oberoi, Mr Satish Sonawane, Tejal Rane and Mahip Shrawagi
Abstract----- Fast transportation systems and rapid
transit systems are nerves of economic developments for
any nation. As the number of road users constantly
increases, and resources provided by current
infrastructures are limited, intelligent control of traffic
will become a very important issue in the future.
Congestion results due to heavy traffic at a junction. Lot
of man-hours are being wasted in travelling due to bad
traffic management. To avoid congestion there are so
many traffic management techniques available.
We have made an attempt to provide some traffic
management technique using our Intelligent Traffic
Control project so as to change real time traffic
scenarios.
(I) Introduction
Conventional traffic control uses timing, which is
inefficient due to varying vehicle density at different roads.
There is a great need for the introduction of advanced
technology and equipment to improve the existing ways of
traffic control as the problem of urban traffic congestion
spreads. The traffic problems are increasing nowadays due
to the growing number of vehicles and the limited resources
we are provided by the infrastructures.
To solve the problem of traffic congestion many
techniques have been applied. Sensors based on closed loop
control algorithms were designed based on emission of
ultrasonic waves, magnetic loops etc. but they have
problems of high cost of installation and maintenance and
also poor accuracy in varying traffic conditions. Hence,
sensors based on image processing were considered an
attractive alternative.
But in the past they too suffered from issues such as
complexity of image processing algorithms and also high
cost of hardware needed for processing. But due to recent
developments in field of computing, hardware costs have
significantly reduced and special dedicated image
processing softwares are available now. This has made
image processing a clear winner for solving traffic
congestion problems.
Prof Mrs Priti Tyagi is working as HOD of Electronics Department and Mr
Sandeep Oberoi, Mr Satish Sonawane, Tejal Rane and Mahip Shrawagi are
Pursuing BE, all are from Padmabhushan Vasantdada Patil Pratishthan’s
College of Engineering, Emails: Hodelex_pvpp@gmail.com,
sandeepoberoi329@gmail.com, satishs088@gmail.com,
tejal.r89@gmail.com, mahipshrawagi@ymail.com
Two main trends are noticeable in studies related with
measurement of traffic flow. One aims to algorithms that
use reduced parts of the image (Inigo, 1985; Inigo,1989;
Michalopoulos, 1991) the other is concerned with
algorithms that use the complete image (J3losseville and
Lenoir, 1989; Hoose, 1991). According to the available
literature, there does not exist a system that can overcome
all the inconvenient distortions due perspective, changing
weather conditions, shades and reflections, varied vehicles
shapes, processing time and so on, seem still to be problems
that each system have solved only partially. Therefore the
problem is still open.
The main step in our system is to perform thresholding
of the grayscale image. Thresholding should be appropriate
so that counting of cars on the roads is accurate.
Hardware Module
Image sensors: In this project a USB based web camera has
been used.
Computer: A general purpose PC as a central unit for
various image processing tasks has been used.
Platform: consisting of a few toy vehicles and LEDs
(prototype of the real world traffic light control system).
Software Module:
MATLAB version 7.8 as image processing software
comprising of specialized modules that perform specific
tasks has been used.
Interfacing: The interfacing between the hardware rototype
and software module is done using parallel port of the
personal computer. Parallel port
(II) Steps in Image Processing
1. Image Representation
Image representation is concerned with characterization of
the quantity that each picture-element (pixel) represents.
The fundamentals requirement of digital processing is that
images can be sampled and quantized. Image can be
represented in analog or digital form. In digital
representation, image can be represented in gray-scale or
colour format. The gray-level images are represented as 8-
bits which allow 256(0-255) possible gray colour

combinations. The colour images are represented as 24-bits
(32-bits including alpha transparency) in which each 8-bits
represents red, green and blue colours.
2. Image Enhancement
In Image enhancement, the goal is to accentuate certain
image features for subsequent analysis or for image display.
Examples include contrast and edge enhancement is useful
in feature extraction, image analysis, and visual information
display. The enhancement process itself does not increase
the inherent information content in the data. It simply
emphasizes certain specified image characteristics.
Fig 1 Image Enhancement Sample
3. Image Restoration
Image restoration refers to removal or minimization of
unknown degradations in an image. This includes deblurring
of images degraded by the limitation of sensor or its
environment, noise filtering, and correction of geometric
distortion or non- linear ties due to sensors
4. Edge Detection
The image consists of objects of interest displayed on a
contrasting background; an edge is a transition from
background to object or vice versa. The total change in
intensity from background to foreground is called the
strength of the edge or edge
Fig 2 Edge Detection of Multiple Cars
5. Histogram Calculation
The histogram of an image represents the relative frequency
of occurrence of the various gray levels in the image. The
histogram of a digital image with gray levels in the range
(0,l-1) is a discrete function.
P (rk) = nk /n
Where, rk is the kth gray level nk is the number of pixels in
the image with that gray level n is the total number of pixels
in the image k=0,1,2,...n-1.
Fig 3 Histogram Analysis
(III) Types of image features
 Edges:
Edges are points where there is a boundary (or an edge)
between two image regions. In general, an edge can be of
almost arbitrary shape, and may include junctions. In
practice, edges are usually defined as sets of points in the
image which have a strong gradient magnitude.
Furthermore, some common algorithms will then chain high
gradient points together to form a more complete description
of an edge. These algorithms usually place some constraints
on the properties of an edge, such as shape, smoothness, and
gradient value.
Locally, edges have a one dimensional structure.
 Corners
The terms corners and interest points are used somewhat
interchangeably and refer to point-like features in an image,
which have a local two dimensional structure. The name
"Corner" arose since early algorithms first performed edge
detection, and then analysed the edges to find rapid changes
in direction (corners). It was then noticed that the so-called
corners were also being detected on parts of the image
which were not corners in the traditional sense (for instance
a small bright spot on a dark background may be detected).
These points are frequently known as interest points, but the
term "corner" is used by tradition.

 Blobs
Blobs provide a complementary description of image
structures in terms of regions, as opposed to corners that are
more point-like. Nevertheless, blob descriptors often contain
a preferred point (a local maximum of an operator response
or a center of gravity) which means that many blob detectors
may also be regarded as interest point operators. Blob
detectors can detect areas in an image which are too smooth
to be detected by a corner detector.
Consider shrinking an image and then performing corner
detection. The detector will respond to points which are
sharp in the shrunk image, but may be smooth in the original
image. It is at this point that the difference between a corner
detector and a blob detector becomes somewhat vague. To a
large extent, this distinction can be remedied by including
an appropriate notion of scale. There are several motivations
for studying and developing blob detectors. One main
reason is to provide complementary information about
regions, which is not obtained from edge detectors or corner
detectors. In early work in the area, blob detection was used
to obtain regions of interest for further processing. These
regions could signal the presence of objects or parts of
objects in the image domain with application to object
recognition and/or object tracking. In other domains, such as
histogram analysis, blob descriptors can also be used for
peak detection with application to segmentation.
Fig 4 Blob Detection
 Ridges:
For elongated objects, the notion of ridges is a natural tool.
A ridge descriptor computed from a grey-level image can be
seen as a generalization of a medial axis. From a practical
viewpoint, a ridge can be thought of as a one-dimensional
curve that represents an axis of symmetry, and in addition
has an attribute of local ridge width associated with each
ridge point. Unfortunately, however, it is algorithmically
harder to extract ridge features from general classes of
grey-level images than edge-, corner- or blob features.
Nevertheless, ridge descriptors are frequently used for road
extraction in aerial images and for extracting blood vessels
in medical images—see ridge detection.
Fig 5 Ridge Detection
Overview of the system
 Capture Image
 Convert to gray scale
 Gray to Binary scale
 Calculate Traffic density
 Led will glow
 Current traffic on road will be uploaded and
message will be sent to the control room accordingly.
(IV) DESCRIPTION OF PROJECT
Two traffic control techniques, cyclic and acyclic, are
widely used. In ATCS, time is distributed cyclically to each
road of the intersection. The roads on each intersection are
assigned names as Road A, Road B, Road C and Road D as
shown in Fig. 1. Each road has a standard set of signals
namely red, yellow and green. During initialization the
camera is rotated by 90 degrees after every 2 seconds to take
the pictures of all roads on intersection. All the signals on
intersection are turned red at this moment. After the images
have been processed, time is assigned to each road
according to its traffic density as Time A, Time B, Time C
and Time D. The green signals are turned on in sequence
starting from Road C to Road D to Road A to Road B and
back to Road C. Camera position is adjusted in such a way
so that it is always two steps ahead from the road signal
which has been turned green. For example, if green signal of
Road C is turned on, then camera will be pointing towards
Road A. The camera will capture Road A conditions after
the time “Time C-Snap Time” is elapsed and moved to next
position, Road B. Snap Time is fixed at 3 seconds. After the
calculated time for Road C is passed, its green signal is
turned off and green signal of Road D is turned on. The state
of the signal is changed with a delay of 1 second in between.
The complete sequence of signals for ATCS is shown in the
Table.

Table 1 Working of the System
Fig 6 Experimental Setup
Image Analysis
The acquired image from the camera is processed to
calculate the total covered area of vehicles on the road. The
greater the number of vehicles in region of interest on the
road, the greater will be the covered area and more will be
the time assigned to that road. The main steps of image
processing are described below:
1) Region of Interest (ROI) Selection: The main objective
for selecting a region of interest (ROI) is to filter out
undesired information present on roads. First of all,
pictures of all empty roads of intersection are captured
and saved. Since the image is a matrix, so some desired
rows and columns are deleted from these images and
these are then saved as region of interest images. This
process of selecting a portion of the original image is
also known as cropping of image.
2) Conversion to Grayscale: The acquired image of actual
road condition is converted into grayscale image with
histogram equalization process for improving the image
contrast.
3) Conversion to Binary: The grayscale image is converted
into binary format
4) Applying ROI: The converted binary image is anded
with ROI image on pixel by pixel basis to remove the
undesired area.
5) Edge Detection: The edges are then found in the
resulting image using the sobel edge detection method. It
returns edges at those points where the gradient of image
is maximum.
6) Morphological Operations: The resulting image with
edges is first eroded using disk as structuring element to
remove noise. It is then dilated with line as structuring
element to remove the discontinuities in object edges
making the boundaries continuous.
7) Road Time Calculation: White pixels in image are
then counted for allocating the time to signals of all
roads at intersection. More white pixels will correspond
to denser road and hence more time will be assigned.
Fig 7 Complete Process of Image Conversion

OUTPUT/SCREENSHOTS
OUTPUT :
Sizeblob 1 = 5 671
The number of cars on 1st road detected are 1
Sizeblob 2 = 1 663 483
The number of cars on 2nd road detected are 2
Sizeblob 3 = 632 652 671
The number of cars on 3rd road detected are 3
The number of cars on 4th road detected are Absence of
cars
SCREENSHOTS
Fig 8 Video Feed from Camera
Fig 9 Grayscale Image of Traffic Signal
Fig 10 Image of Road 1
Future Enhancements
 The present system has a single camera mounted for a
particular junction. In future, a separate camera for each
road at an intersection will allow the system to use video
processing which can improve the system efficiency
further.
 The vehicle objects can also be categorized into various
classes depending upon the geometrical shape of vehicle
for blocking the passage of large vehicles e.g., trucks
during day times. This will further help our cause in
managing the traffic.

 Also, the entire system can be collaborated with a GSM
Interface enabling the signals to be controlled via Mobile
phones in case of an emergency. This might be
beneficial in case of ambulance, police or fire brigade.
Summary and Conclusions
The study showed that image processing is a better
technique to control the state change of the traffic light. It
shows that it can reduce the traffic congestion and voids the
time being wasted by a green light on an empty road. It is
also more consistent in detecting vehicle presence because it
uses actual traffic images. It visualizes the reality so it
functions much better than those systems that rely on the
detection of the vehicles’ metal content. Overall, the system
is good but it still needs improvement to achieve a hundred
percent accuracy.
REFERENCES
[1] A.Soto , A. Cipriano, “Image processing applied to
real-time measurment of traffic flow,” in Proceedings
of the Twenty-Eighth South eastern Symposium on
System Theory, 1997.
[2] Umar Farooq, Hafiz Muhammad Atiq, Muhammad
Usman Asad, Asim Iqbal, “Design and Development of
an Image Processing Based Adaptive Traffic Control
System with GSM Interface,” in International
Conference on Machine Vision, 2009.
[3] Image processing toolbox help, MATLAB® [Online].
Available: http://www.mathworks.com/
[4] Rafel C. Gonzalez and Richard E. Woods, Digital
Image Processing, Pearson Education, 2004.
[5] J. Canny (1986) "A computational approach to edge
detection", IEEE Trans. Pattern Analysis and Machine
Intelligence, vol 8, pages 679-714.
[6] T. Lindeberg (1998) "Edge detection and ridge
detection with automatic scale selection", International
Journal of Computer Vision, 30, 2, pages 117--154.
[7] AT89S52 information and help. Available:
http://www.8051.net/ http://www.8051projects.com/
[8] R. Rad, and M. Jamzad, “Real time classification and
tracking of multiple vehicles in highways,” Pattern
Recognition Letters, vol. 26, no. 10, 15 July 2005, pp.
1597-1607.

1. control of real time traffic with the help of image processing

More Related Content

What's hot (20)

Viewers also liked (20)

Similar to 1. control of real time traffic with the help of image processing (20)

Recently uploaded (20)

1. control of real time traffic with the help of image processing