ISSN (Print) : 2319-5940

ISSN (Online) : 2278-1021

International Journal of Advanced Research in Computer and Communication Engineering

Vol. 2, Issue 6, June 2013

Traffic Load Computation using Matlab Simulink

Model Blockset
Pratishtha Gupta 1, G.N Purohit 2, Adhyana Gupta 3
Assistant Professor, Computer Science, Banasthali Vidyapith,Jaipur, India 1
Professor, Computer Science, Banasthali Vidyapith,Jaipur, India 2
M.Tech Student, Computer Science, Banasthali Vidyapith,Jaipur, India 3

Abstract: Real time traffic signal control is a serious issue to be resolved to control the increasing traffic congestion. This
paper outlines an efficient simulation model for counting the vehicles from the colored and gray-scale images through
image processing techniques in Simulink environment. Video and Image Processing Blockset is a tool used for the rapid
design, prototyping, graphical simulation, and efficient code generation of video and image processing algorithms. The
approach used is morphological operation (Opening) which works very effectively for images captured. The developed
process involves object feature identification, detection, and counting objects.

Keywords: Matlab, Morphological Operations, Vehicle detection, Simulink, video and Image processing

I. INTRODUCTION intelligent and real time. Here, a very brief overview of

In recent years, the application of image processing some of these research works has been presented.
techniques in automatic traffic signal control has been Chen et al. [1] analyzed existing video object
investigated by several researchers. The major problem segmentation algorithms and found that most of the core
concerning automatic traffic signal control is to compute the operations can be implemented with simple morphology
traffic load from the images captured. operations. Therefore, with the concepts of morphological
This document aims at counting the vehicles in the image processing element array and stream processing, a
traffic images captured for real time traffic signal control reconfigurable morphological image processing accelerator
using video and image processing Blockset in Simulink is proposed, where by the proposed instruction set, the
Environment of MATLAB. The Video and Image operation of each processing element can be controlled, and
Processing Blockset contains blocks that perform the interconnection between processing elements can also
morphological operations such as erosion, dilation, opening be reconfigured.
and closing. Simulink Blockset contains display block, label Christe et al. [2] focused on processing an image
block, relational operator and constant block. pixel by pixel and in modification of pixel neighborhoods
The combination of these blocks is used to perform and the transformation that can be applied to the whole
morphological image analysis. Morphology is the study of image or only a partial region.
the shape and form of objects. Morphological image analysis Al-amri et al. [3] have proposed segmentation
can be used to perform image filtering, image segmentation, algorithms based on one of two basic properties of
and measurement operations. intensity values discontinuity and similarity. First
A Simulink model has been developed using category is to partition an image based on abrupt changes
different image processing blocksets . The developed in intensity, such as edges in an image. Second category
approach eliminates the tiny elements from the image, then is based on partitioning an image into regions that are
creating segments and then counting the number of vehicles. similar according to predefined criteria.
The remainder of the paper is organized as follows. Suthar A.C. et al. [4] have focused on pixel to
Section 2 briefly presents the related work. Section 3 briefly pixel processing of an image and in the modification of pixel
describes the experimental environment being used for this neighborhoods and of course the application of
study. Section 4 presents the approach developed to count transformation to the whole image or only a partial region.
the number of vehicles in the input image. Section 5 draws Shinde B. et al. [5] s t a t e that image processing
the conclusion. operations can be roughly divided into three major
II. RELATED WORK categories, Image Compression, Image Enhancement and
Extensive work has been done in the field of image Restoration, and Measurement Extraction. It involves
processing in order to make the traffic control system reducing the amount of memory needed to store a digital

Copyright to IJARCCE www.ijarcce.com 2427

 ISSN (Print) : 2319-5940
ISSN (Online) : 2278-1021

International Journal of Advanced Research in Computer and Communication Engineering

Vol. 2, Issue 6, June 2013

image. Once the image has been digitized, it can be operated B. Video and Image Processing and Signal Processing
upon by various image processing operations.
Kastrinaki et al. in [6] pr esent an overview of System objects are algorithms that provide stream
image processing and analysis tools used in these processing, fixed-point modeling, and code generation
applications and we relate these tools with complete capabilities for use in MATLAB programs. These new
systems developed for specific traffic applications. Image objects allow one to use video and image processing
processing also finds extensive applications in the related algorithms in MATLAB, providing the same parameters,
field of autonomous vehicle guidance, mainly for numeric’s and performance as corresponding Video and
determining the vehicle’s relative position in the lane and Image Processing Blockset blocks. System objects can also
for obstacle detection. be used in Simulink models via the Embedded MATLAB
Mahalanobis et al. [7] explain the detection and Function block. Simulink environment provide platform for
tracking of humans as well as vehicles is of interest. The model-Based Design and code generation out of a user-
three main novel aspects of the work presented in this Friendly block diagram environment. (Fig. 1and Fig.
paper are i) the integration of automatic target detection 2)Video and Image Processing Blockset blocks support
and recognition techniques with tracking ii) the handover floating‐point, integer, and fixed‐point data types. To use
and seamless tracking of objects across a network, and any data type other than double‐precision and
iii) the development of real-time communication and single‐precision floating point, you must install Simulink
messaging protocols using COTS networking Fixed Point.
components.
Ramadevi et a l . [8] discussed in this paper image C. Parameters
segmentation is to partition an image into meaningful
regions with respect to a particular Application. Image Opening Block Parameter: Use the Neighborhood or
segmentation is the process of partitioning/subdividing a structuring element parameter to define the neighborhood or
digital image into multiple meaningful regions or sets of structuring element that apply to the image. Specify a
pixels regions with respect to a particular application. neighborhood by entering a matrix or vector of ones and
Bhat et al. [9] discussed Object tracking is used to zeros. Specify a structuring element using the strl function.
describe the process of recording movement and translating Alternatively, you can specify neighborhood values using
that movement onto a digital model. Simulink with Video the Nhood port.
and Image processing Blockset enable to run fast Label Block Parameters: At the Label port, the block
simulations for real-time embedded video, vision, and outputs a label matrix where pixels equal to 0 represent the
imaging systems. background, pixels equal to 1 represent one object and pixels
Arora et al. [10] discussed two techniques for equal to 2 represent the second object, and so on. At the
traffic light control. Firstly we have discussed morphological count port, block outputs a scalar that represents the number
method of edge detection for real time traffic control and of labeled objects.
then fuzzy logic.

III. EXPERIMENTAL ENVIRONMENT

Executable
A. Matlab Specifications
from Models
MATLAB (matrix laboratory) is a numerical computing
environment and fourth-generation programming language.
MATLAB allows matrix manipulations, plotting of
functions and data, implementation of algorithms, creation Continuous
Simulink Design with
of user interfaces, and interfacing with programs written in Test and
Models Simulation
other languages, including C, C++, Java, and Fortran. Verification
Although MATLAB is intended primarily for numerical
computing, an optional toolbox uses the MuPAD symbolic
engine, allowing access to symbolic computing capabilities.
An additional package, Simulink, adds graphical multi- Implimentation
domain simulation and Model-Based Design for dynamic with Automatic
and embedded systems. Code Generation
Figure 1:Simulink Model

Copyright to IJARCCE www.ijarcce.com 2428

 ISSN (Print) : 2319-5940
ISSN (Online) : 2278-1021

International Journal of Advanced Research in Computer and Communication Engineering

Vol. 2, Issue 6, June 2013

Figure 2:Video and Image Processing Library Browser

D. Morphological Operators
Morphological operators have a wide variety of uses, Figure 4:Blocks Quantity
including correcting non uniform illumination, enhancing and Label blocks, the numbers of vehicles in the
contrast, removing noise, and thinning regions.
Morphological operators in Video and Image Processing
image are counted.
1. Import the target image from MATLAB workspace
Blockset include:
and view the image. (Fig. 3)
▪ Erosion and dilation
2. Create a new Simulink model, and click-and-drag
▪ Opening and closing
the following blocks into it. (Fig. 4)
▪ Labeling of connected components
3. The unconnected blocks are arranged as shown in
▪ Top-hat and bottom-hat filtering
the figure. (Fig. 5)
Block parameters are set by double clicking and
IV. EXPERIMENT AND RESULTS
modifying the block parameters values.
An intensity image of the traffic image is imported and
4. Image from Workspace block is used to import the
converts it to binary. Then, using the Opening
target image from MATLAB workspace.

Figure 3:Original image Figure 5:Unconnected Blocks

Copyright to IJARCCE www.ijarcce.com 2429

 ISSN (Print) : 2319-5940
ISSN (Online) : 2278-1021

International Journal of Advanced Research in Computer and Communication Engineering

Vol. 2, Issue 6, June 2013

Label block expects binary input. Also, the objects

it counts must be white.
8. The Opening block to separate the vehicles from
the image and from each other at the image. Use the
default parameters. (Fig. 6)
The strel function creates a circular STREL object
with a radius of 5 pixels. With the Opening block,

Figure 6:Opening block parameters set

Figure 8:Connected blocks

Figure 7:Label block parameters set

Block parameters are set as given below:

 Main pane, Value = I
 Main pane, Output port labels = Image

5. Constant block is used to define a threshold value

for the Relational Operator block. Set the Constant
value parameter to 200.
6. Video Viewer1 block is used to view the original
Figure 9:Original image
image. Set the Input image type parameter to
Intensity.
7. Relational Operator block is used to perform a
thresholding operation that converts the intensity
image to a binary image. Relational Operator
parameter is set to <.
If the input to the Relational Operator block is less
than 200, its output is 1; otherwise, its output is
0.Threshold of intensity image is must because the
Copyright to IJARCCE www.ijarcce.com 2430
 ISSN (Print) : 2319-5940
ISSN (Online) : 2278-1021

International Journal of Advanced Research in Computer and Communication Engineering

Vol. 2, Issue 6, June 2013

12. The blocks are connected as shown in the figure.

(Fig. 8)
13. The configuration parameters are set. Configuration
dialog box is opened by selecting Configuration
Parameters from the Simulation menu. The
parameters are set as follows:
 Solver pane, Stop time = 0
 Solver pane, Type = Fixed-step
 Solver pane, Solver = discrete (no
continuous states)
Result:
14. The original image appears in the Video Viewer1
window. (Fig. 9)
15. The opened image appears in the Video Viewer
window. The vehicles are separate white objects
(Fig.10)
16. The Opening and Label blocks to count the number
Figure 10:Separated Vehicles
of vehicles in an image. (Fig. 11)

STREL object that fits within the objects to be kept

is picked.
9. Video Viewer block is used to view the opened
image. Input image type parameter is set to
Intensity.
10. The Label block is used to count the number of
vehicles in the input image. Set the Output
parameter is set to Number of labels. (Fig. 7)
11. Displays the number of vehicles in the input image.
Use the default parameters.

Figure 11:Count number of vehicles (Final Result)

V. CONCLUSION useful to detect the traffic on road. Hence, the suggested
In this paper, an image processing algorithm suitable for algorithm proves to be an efficient solution for computing
traffic load computation has been suggested and analyzed. traffic load in order to make traffic signal control system
The developed Simulink model is reliable and can perform dynamic.
vehicle counting on roads. This Simulink model will be
Copyright to IJARCCE www.ijarcce.com 2431
 ISSN (Print) : 2319-5940
ISSN (Online) : 2278-1021

International Journal of Advanced Research in Computer and Communication Engineering

Vol. 2, Issue 6, June 2013

REFERENCES BIOGRAPHY
[1] Chien S.Y. ,Chen L.G., “Reconfigurable Morphological Image
Processing Accelerator for Video Object Segmentation”, springer, J Prof. G. N. Purohit is a Professor in
Sign Process Syst (2011) 62:77–96, DOI 10.1007/s11265-008-0311-6 Department of Mathematics & Statistics at
[2] Christe S.A., Vignesh M., Kandaswamy A., “An efficient FPGA Banasthali University (Rajasthan). Before
implementation of MRI image filtering and tumour characterization joining Banasthali University, he was
using Xilinx system generator”, International Journal of VLSI Professor and Head of the Department of
design & Communication Systems (VLSICS), Vol.2 ,No.4, December Mathematics, University of Rajasthan, Jaipur.
2011 He had been Chief-editor of a research journal
[3] Al-amri S.S., Kalyankar N.V., Khamitkar S.D, “Image and regular reviewer of many journals. His
Segmentation by Using Threshold Techniques”, journal of present interest is in O.R., Discrete
computing, volume 2, issue 5, may 2010, ISSN 2151-9617 Mathematics and Communication networks.
[4] Suthar A. C., Vayada M., Patel C. B., Kulkarni G.R., Hardware Software He has published around 40 research papers
co-simulation for Image Processing Applications”, IJCSI International in various journals.
Journal of Computer Science Issues, Vol. 9, Issue 2, No 2, March
2012 Pratishtha Gupta is an active researcher in
[5] Shinde B., Mhaske D., Dani A.R., “Study of Image Processing, the field of image processing, currently
Enhancement and Restoration”, IJCSI International Journal of working as Assistant Professor in Department
Computer Science Issues, Vol. 8, Issue 6, No 3, November 2011 of Computer Science at Banasthali
[6] Kastrinaki V., Zervakis M., Kalaitzakis K., “A survey of video University(Rajasthan), India. She has done
processing techniques for traffic applications”, Image and Vision M.Sc (CS) and B-Level and undergoing PhD
Computing 21 (2003) 359–381, doi:10.1016/S0262-8856(03)00004-0 from Banasthali University (Rajasthan), India.
[7] Mahalanobis A., Cannon J., Stanfill S.R., Muise R., Martin L.,
“Network Video Image Processing for Security, Surveillance, and
Situational Awareness”, Proc. SPIE 5440, Digital Wireless
Communications VI,1 (August 10, 2004); doi:10.1117/12.548981
[8] Ramadevi Y., Sridevi T., Poornima B., Kalyani B., “Segmentation Adhyana Gupta is an active researcher in the
and object recognition using edge detection techniques” , field of image processing, currently studying
International Journal of Computer Science & Information in M.Tech (IT) from Banasthali University,
Technology (IJCSIT), Vol 2, No 6, December 2010 Rajasthan. She received M.Sc Degree in
[9] Bhat M., Kapoor P., Raina B.L.,“Application of sad algorithm in Computer Science from Makhanlal
image processing for motion detection and simulink blocksets for Chaturvedi National University of Journalism
object tracking”, [IJESAT] international journal of engineering and Communication, Bhopal in 2008.
science & advanced technology, Volume-2, Issue-3, 731 – 736
[10] Arora M., Banga V. K., “Real Time Traffic Light Control System
Using Morphological Edge Detection and Fuzzy Logic”, 2nd
International Conference on Electrical, Electronics and Civil
Engineering (ICEECE'2012) Singapore April 28-29, 2012

Copyright to IJARCCE www.ijarcce.com 2432