IRJET- Time To Cross – Traffic Light Control System using Image Processing

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 918
Time To Cross – Traffic Light Control System using Image Processing
Anju Jaison1, Evita Varghese2, Gopika K G3, Krishnadas J4
Kerala, India
4 Assistant Professor, Dept. of Computer Science Engineering, Sahrdaya College of Engineering & Technology,
Kerala, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract –Over the past decades, increasing traffic volume
posses many challenges in the society. There are many
accidents happening these days due to careless behaviorofthe
pedestrians and vehicles at the traffic signal. In this paper we
bring an idea of smart traffic control system using image
processing by integrating it into an existing CCTV camera
commonly installed on street poles. The cameras placedonthe
street poles, one will be focusing on the pedestrian and other
on vehicles. Both cameras will be capturing images. Then
using image processing the density of pedestrianandvehiclein
respective images are taken and compare. If the trafficdensity
of vehicles is more than a particular limit and density of
pedestrian is normal, then vehicle mode will be on.Ifthetraffic
density of pedestrian is more than a particular limit and
density of vehicle is normal, then pedestrian mode will be on.
When pedestrian mode happened, the microcontroller will
send the signal to the connecting speaker to notify those
pedestrians about crossing time. If the density of both
pedestrian and vehicle more than limit, then there will be a
traffic cycle which gives equal time interval for both teams to
cross the signal. The system was composed of camera, PIC
microcontroller for traffic signal and recorded voice notifier
using a portable speaker. The motto behind this research is to
reduce the conflict at the traffic by giving equal importanceto
both vehicles and pedestrian.
Key Words: traffic volume, smart traffic control system,
traffic density
1. INTRODUCTION
Traffic mobbing is a major problem in developed cities. In
this traffic mobbing scenarios peoples are wasting vehicles
fuel and unable to utilized their time [2]. High utilization of
present road capacity by managing traffic efficiently is very
important. Due to these traffic congestion people’s daily
schedules getting disturbed as well as some are going
through critical cases [3][5]. If we take example of
ambulance having patient in critical conditionsandifthereis
traffic jam on that road, then there are high chances that
ambulance will not be able to reach hospital in time. Due to
situations like these human lives are in danger. That’s why
there is need of dynamic intelligent traffic control system
who can able to handle these traffic conditions efficiently to
circumvent traffic crowding and accidents situations [4][5].
As the problem of urban traffic congestion spreads,. there is
a pressing. need for the introductionof advancedtechnology
and equipment to improve the state-of-the-art of traffic
control. Traffic problems nowadays are increasing because
of the growing number of vehicles and the limited resources
provided by current infrastructures. The simplest way for
controlling a traffic light uses timer for each phase. Another
way is to use electronic sensors in order to detect vehicles,
and produce signal that cycles. Besides, the highway and
roads are incapable of meeting the requirementofincreasing
number of vehicle. Instead of working on roads to
accommodate the growing traffic various techniques have
been devised to control the traffic on roads like embedded
controllers that are installed at the junction.
We propose a system for controlling the traffic light by
image processing. The system will detect the density of
vehicles and pedestrians through images instead of using
electronic sensors embedded in the pavement. Cameras will
be installed alongside the traffic light or street poles. They
will capture image sequences. The image sequence will then
be analyzed using digital image processing for vehicle and
pedestrian density, and according to the density of both
pedestrian and vehicle on the road traffic light can be
controlled.
2. SYSTEM DESIGN
The work is dividing into 4 parts. The first part is to process
the video signal of pedestrian and vehicle captured through
the existing cameras using Image Processing. The second
part is to changing timer according to density of the traffic
after the image processing. The third part is to send the
signals to the Microcontroller for control the traffic lights.
The final part of this work is to send the signal to thespeaker
to notify the people about the traffic light.Block diagram of
the proposed system is given below.
A. Real Time Image Processing
A system having the cameras which connected to the
processor is installed on the traffic light. In a trafficlightarea
two cameras are installed , one is to monitor the vehicles on
that lane and other is for pedestrians. Camera will give the
traffic images to the processor. In processor, Image
Processing algorithms were there which will process the
image to extract out the needful information in short spanof
time.
1,2,3 B.Tech Student, Dept. of Computer Science Engineering, Sahrdaya College of Engineering & Technology,

Fig -1 : Proposed traffic control system model
In this system OpenCV(Open Computer Vision) is used for
the image processing. It is the field of informatics which
teaches the computers to see. It is a way computers gather
and interpret visual information from the surrounding
environment.
B. Changing Timer according to traffic density
Timers for the traffic signals are changing according to the
output of algorithms. Two cases are made out from the
above algorithms.
1) Using Cascade classifier gives the vehicle density count
on the road as shown in Fig 2. Cascade classifier is used to
detect the objects in the video stream. This algorithm is
capable of differentiating vehicles from different objects.
2) Using Histogram of Oriented Gradient, gives the
pedestrian count on the road asshown in Fig 3. Accordingto
the observation, the timer for the pedestrian on the traffic
will change.
Fig – 2: Cascade Classifier applied on running video
According to the traffic density obtained after Image
processing, the corresponding signal is sent to the
microcontroller attached with the traffic light. It will control
the traffic light according to the signal from the processor.
Only one microcontroller is used to control the traffic light
for both pedestrian and vehicle.
Fig – 3: Human Detection Using HOG
C. Sending signals to the Speaker
This system notifies the user about the traffic light. A
portable speaker is attached with the system. According to
the traffic mode coming next the signal is sent to the speaker
to notify the users about it. The aim of using this voice
notification is to notify the blind people who are waiting at
the traffic to cross the road.
3. WORKING AND EXPERIMENTATION
In this paper, we used two algorithms to manage traffic
signal lights. We have implemented these in OpenCV :
Cascade classifier and Histogram of OrientedGradient(HOG)
algorithms. Through object recognition, total number of
vehicles in front of the cameras can be found out. The count
of vehicles and pedestrian are given to the microcontroller.
According to the count, the microcontroller will change the
timer of traffic light on that lane. Cascade classifier needs to
be trained for accurate result after processing. This method
is used for the detection of the vehicles on the lane. The
reason behind using this method is it will give high level of
precision and recall when detecting objects in images.Inthis
system cascade classifier isused to detect the vehicles in the
lane. Second method is Histogram of Oriented
Gradient(HOG), in whichobject appearanceandshapecanbe
described by pixel gradient distribution. This algorithm is
used in this project, to take the count of pedestrian who are
waiting at the signals to cross the road.HOG is the best
algorithm for the human detection, is the reason behind
using this algorithm. For traffic density, there is a particular
limit for both the vehicles and pedestrian. Based on this
limit,the traffic timer is changed for the signals.

With the help of Microcontroller, image processing the
problems at the traffic intersection can be solved. Processor
will do the image processing part. The second part is to
change the traffic timer according to the traffic density,
microcontroller will do this. Third part is to send the signals
to the speaker to notify the people in the traffic to cross the
road. The flow diagram for the system is given in Fig 4.
Fig – 4 : Flowchart of the system
To implement traffic control system, we have used PIC
microcontroller with OpenCV. This system mainly consist of
two parts ie., Hardware part and Software part. In hardware
part, two cameras are attached to traffic lights in the system
which is attached to the microcontroller. Camera and
microcontroller is connected to the processor through a
wired medium. The cameraswill feed the processorwiththe
image of both vehicles and pedestrian at the traffic. The
processor responsibility is to process the image and give
useful output from these images. From imageonecanextract
out many details like time taken by vehicles to pass the
signal, waiting time of vehicles, route which is moresuitable,
cars present on the lane, empty area of the lane etc.
Management of traffic and coordination of traffic lights (in
case of intersection) is possible because of these results.
Traffic timers can be changed according to the output of the
OpenCV algorithm. The traffic light are managed and
coordinated in such a way that it will reduce the conflict at
the traffic by giving equal importance to bothpedestrianand
vehicles.
4. RESULT
In our experiment, we have used a set of videos to
demonstrate the switching of traffic light signals. The video
set consist of both pedestrian and vehicles. The system
detects the vehicles and pedestrian as shown in fig 5.
Fig – 5: Object detection by the system
These densities are compared with predefined limit of
vehicles and pedestrian respectively. If the pedestrian
density is greater than the predefined limitofpedestrianand
vehicle density is normal, then pedestrian mode is on along
with an audio alerting the pedestrian to cross the road. Ifthe
vehicle density is greater than the predefined limitofvehicle
and pedestrian density is normal, then vehicle mode is on.
The following table shows the experimental result of the
system.

Table 1: Experimental Results
Vehicle
Density
Pedestrian
Density
Vehicle
Mode
Pedestrian
Mode
10 2 On Off
15 7 On On
2 7 Off On
5 3 On Off
1 3 Off On
5. CONCLUSION
Traffic condition on roads is one of the big issue especially
for the pedestrian. It is observed that pedestrian needs to
spend lot of time to cross the road near the traffic light.
Nowadays every smart traffic control system tries to solve
the problems of vehicles only. But our current system is a
solution to this problem by giving equal priority to both the
pedestrian and vehicles. The project guarantees that the
average waiting time vehicles and pedestrian at the traffic
signals can be reduced. This system can reduce the conflicts
between the vehicles and pedestrian at the traffic.
REFERENCES
[1] Abay Dubey,Akshdeep,Sagar Rane “Implementation of
an Intelligent Traffic Control System and Real Time
Traffic Statistics Broadcasting,” ICECA 2017, pp.34-
37,vol -17.
[2] Vikramaditya Dangi, Amol Parab, Kshitij Pawar & S.S
Rathod, “Image Processing Based Intelligent Traffic
Controller”, Undergraduate Academic Research Journal
(UARJ), Vol.1, Issue 1, 2012.
[3] Papageorgiou M., Diakaki C., Dinopoulou V., Kotsialos,
A.,“Review of road traffic control strategies”,
Proceedings of IEEE, Vol. 91, Issue 12, pp. 2043-2067,
November 2004.
[4] Georgios Vigos, Markos Papageorgioua, Yibing Wangb,
“Real-time estimation of vehicle-count withinsignalized
links”, Journal of Transportation Research Part C:
Emerging Technologies, Volume 16, Issue 1, pp.18–35,
February 2008.
[5] Michael W. Szeto and Denos C. Gazis, “Application of
Kalman Filtering to the Surveillance and Control of
Traffic Systems”, Journal of Transportation Science, vol.
6 pp.. 4419-439 , November 1972.

IRJET- Time To Cross – Traffic Light Control System using Image Processing

More Related Content

What's hot (20)

Similar to IRJET- Time To Cross – Traffic Light Control System using Image Processing (20)

More from IRJET Journal (20)

Recently uploaded (20)

IRJET- Time To Cross – Traffic Light Control System using Image Processing