Journal of Physics:

Conference Series

PAPER • OPEN ACCESS You may also like

- Analysis and prediction of traffic flow
A Smart Transportation Design System for based on Wavelet-BP neural network
Zhuo Wang and Lei Zhao
Restricted Areas with Vehicle Automation - The Architecture and Development of
Intelligent Traffic Signal Control Platform
Technologies using Raspberry Pi B and Open CV Zhao Wang, Yawen Pan and Mengjie
Wang
Python – An Experimental Approach - Optimizing the traffic control system of
Sultan Agung street Yogyakarta using
fuzzy logic controller
To cite this article: G. Premalatha et al 2021 J. Phys.: Conf. Ser. 1717 012027 L N A Mualifah and A M Abadi

View the article online for updates and enhancements.

This content was downloaded from IP address 152.58.17.18 on 19/04/2025 at 20:24

RASCC 2020 IOP Publishing
Journal of Physics: Conference Series 1717 (2021) 012027 doi:10.1088/1742-6596/1717/1/012027

A Smart Transportation Design System for Restricted Areas

with Vehicle Automation Technologies using Raspberry Pi B
and Open CV Python – An Experimental Approach

G.Premalatha1, K.Dhivya2, M.Sridhar3, S.Sridharan4

1,2
Assistant Professor, IFET College of engineering, IFET
Nagar,Gangarampalayam,Villupuram, Tamil Nadu.
3,4 UG student, IFET College of engineering, IFET
Nagar,Gangarampalayam,Villupuram, Tamil Nadu.

premaglatha07@gmail.com,k.dhivya91@gmail.com, sridharyogi2@gmail.com

Abstract. With the advent of sensors and automation technologies, the intelligent
transportation system has become a horizon in energizing and transforming human lives. It
gains attraction among various communities due to its reduced workforce and efficient
automation. In recent decades, digital advancements stood witnessed as the novel technology
in performing the traffic control regime. However, factors such as over speed, natural disasters,
and human distractions making the traffic system more puzzling. Hence to address the
challenges, the proposed system propounds the novel way of traffic control by taking the
vehicle over-speed as the intended factor. It performs automatic control of vehicle speed to
avoid accidents and to accomplish safe driving in restricted areas. In this system, Raspberry Pi
B microcontroller is utilized to embrace the detection of traffic signals. Additionally, the
ultrasonic sensor is equipped for measuring the distance of the vehicles ahead to it in order to
avoid collisions. Moreover, the R-pi camera module is employed for the detection of traffic
signals and signboards. The real-world images are processed using Open CV python for object
and traffic sign detection. Typically, it performs some intelligent classification of the images
acquired from the camera module. Furthermore, the speed control of the vehicle is facilitated
by the deployment of DC motors connected to the engine. Thus, the proposed system is
designed to achieve the speed control and automation of the vehicle as per the warning signals.
Here, python has used for programming the microcontroller. Also, step by step analysis of the
system is carried out, and the experimental results are shown to visualize the function of the
proposed self-automated vehicle.

1.Introduction
Due to the rapid urbanization and growing number of vehicles, road accidents now endangering the
country and leads to loss of human lives. The factors like over speed, driver distractions, traffic
intensity, and natural calamities are becoming the primary concern in the transportation systems.
Nowadays the road and traffic control systems are widespread in making the communities more alert
in following the driving rules. Also, the safety mechanisms such as automatic speed control [1],
collision warning system [2], and novel driver assistance systems came into existence for intelligent
driving and safer travel. Moreover, due to the advent of sensors and IoT technologies [3], the
automation of vehicles becomes more pervasive, and intelligent Transportation has been ascertained.
In recent decades, the smart vehicles gained attraction among various communities and paves way for
an improvement of economic viability of the technology.
Intelligent travel is now becoming multimodal due to the enhanced forms of transportation in
which the travellers seamlessly connected across every means of travel. Indeed, Intelligent
Transportation Systems (ITS) [4] becomes an attention snatcher by its firm and remarkable benefits
such as navigation support, effective communication, traffic management, and users’ entertainment;
thereby, it becomes an extension of peoples' digital lifestyle. In many advanced applications, smart
city and transportation systems are connected as depicted in Figure 1. Additionally, the technological
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution
of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
Published under licence by IOP Publishing Ltd 1
RASCC 2020 IOP Publishing
Journal of Physics: Conference Series 1717 (2021) 012027 doi:10.1088/1742-6596/1717/1/012027

progression in transportation systems helps proponents across the world with the applications such as
electronic toll collection, license plate detection, traveller information systems, intelligent parking
systems, automatic speed control, railway track crossing public safety, and tracking mechanisms. As
beneficial, it promotes substantial changes in various sectors such as government, tourism, trade, and
logistics. In this context, Intelligent Transport Systems (ITS) is likely to be fascinating by adopting
some modern technologies, which include automation, ubiquitous sensing, and robust tracking
systems. Many learning algorithms facilitate the intelligent transport systems to a greater extent by
employs supervised models for vehicle movement prediction, expert systems for damage mitigation by
pavement monitoring, and deep learning systems for traffic signal automation. At the same time, the
primary goals of Intelligent Transport Systems are to mitigate transportation bottlenecks by ensuring
better decision making and to maintaining the sustainability of available resources.

Fig.1 Coupling of vehicles and smart city

Due to the rapid proliferation of the IoT and automation capabilities, HCI ( Human Computer
Interaction) offers diversified advancements in transports for instance: a) Informing nearby fuel or
recharging stations offers lowest prices b) vehicle passenger monitoring to adapt seating navigation
and entertainment preferences c) vehicle drift and collision monitoring to respond in case of potential
dangers d) Congestion detecting and notifying when heavy traffic detected and e) Enabling automated
intelligent real-time decisions to optimize safe travel. In this proposed system the experimental
approach is carried out using R-Pi and Open CV python [5] to facilitate the intelligent travel. The
automation technologies utilize the existing communication technologies like Zig Bee and Bluetooth
[6] for connecting the sensors to the cloud. The proposed system is modelled using Raspberry Pi B
microcontroller [7-10] to integrate all the vehicle functions. For capturing the real-world images, R-Pi
camera module is used. It assists the vehicle in navigating with the help of traffic signal and sign board
images. Moreover, ultrasonic sensor is used to find the distance of the vehicle ahead to it. It automates
the vehicle according to the intended distance either to stop or run to avoid the chaos. DC motors are
equipped to carry out the speed control of the proposed venture. Python programming is used to
control the entire set up and Open CV is used to model the images of the R-Pi. The reference database
is fetched into the memory of R-Pi which consists of the trained set of traffic images. Hence a finest
automation system is proposed in this work to navigate and automate the vehicles during cautionary

2
RASCC 2020 IOP Publishing
Journal of Physics: Conference Series 1717 (2021) 012027 doi:10.1088/1742-6596/1717/1/012027

incidents. The prototype model is designed in order to show the miniature version of the self-
automated car associated with the above said functions. Also, the communication technologies such as
Bluetooth and Wireless LAN equip the short and long-distance communication.

2. Literature Survey
In this section, various existing approaches for vehicle automation and speed control is discussed. CH.
Madhuri Devi et.al [11] designed traffic sign detection and sign board recognition in which
segmentation algorithms are used. This utilizes Raspberry pi B and ARM processors for controlling
various processors. Also, it employs fabricated sensors and cameras to alert the drivers for further
actions need to be taken. The primary goal of the suggested system is mainly to navigate the vehicles
according to the sign boards detected. Followed by [11], P. A. Shinde and Y. B. Mane proposed a
vehicle monitoring and tracking using GSM and GPS technologies [12]. It alerts the driver if he
chosen a wrong path via mobile devices. Also, the system utilizes the gas leakage sensor and
temperature sensor for vehicle’s safety. Consecutively in [13], fuzzy-PID control based smart vehicle
is designed for smart way of parking in urban areas. MA Khan et.al [14] has suggested a design to
detect and warn the user during the impediments such as object detection, overspeed and traffic
warning signals. It is efficiently programmed for sending the over-speed vehicle information to the
authorities for further action. To carry out the functions, an authorized threshold speed value was set.
If the vehicle crosses the limit it sends the relevant information to the intended centres. In addition,
Digital Image Processing technologies used for immediate license plate detection of the over-speed
vehicles. Thus, the system propounded a novel framework for vehicle detection accompanied with
associated images.

3. Proposed System

3.1. System design

The block diagram of the proposed system is depicted in figure 2. The proposed system consists of a
Raspberry Pi which acts as the central part of the self-automated vehicle. It consists of a power supply
for the microcontroller and the connected devices to run the system. It connected to the rectifier to
convert the incoming AC power supply to the DC values. Further, it connects with the regulator to
reduce the abundant power supply to limit the range that the raspberry module can resist. To convert
the high voltage to the low voltage input the regulator is used. Then LCD display is meant for viewing
the functions of the system. Camera module V2 is connected to the GPIO pin to capture the traffic
signs and objects. The Bluetooth module of specification BLE 4.0 is used to connect wirelessly with
the controller. Furthermore, to detect the objects and to automate the vehicle automatically, the
ultrasonic sensor of specification HC-SR04 is equipped. In order to automate the vehicle function,
Motor driver IC l293d is connected to the microcontroller. Significantly, the traffic board signal
images and stop boards are fetched in the internal memory for further processing.

3
RASCC 2020 IOP Publishing
Journal of Physics: Conference Series 1717 (2021) 012027 doi:10.1088/1742-6596/1717/1/012027

Fig.2 Block diagram of the self-automated car

3.2 An automated vehicle-speed control with OpenCV python and Raspberry Pi B

Open CV (Computer Vision) is a library package intended for objects and image detection of real-time
images. The proposed system uses the Open CV for processing the traffic signals and sign boards. The
images that are acquired from the camera module are then fed into masking and contour techniques for
detecting the sign boards and red signals of the traffic ecosystem. Python 3 IDLE is used for
programming the microcontroller.
The main objective of the proposed system is to detect the sign boards and stop boards located in
the road sides. It is designed to further automate the vehicle accordingly. More often, the red signal
system is recognized as the rectangle that lies between the topmost and least bound extremities of the
red signals as shown in figure 3. In this system, the fixed area is determined by rectangle formed by
the red light and the geometric shape is give as input to the GPIO pin. Normally it is used to control
the vehicle by automate the motors as programmed. In order to detect the stop boards, the proposed
system uses the cascade classifier[17-20]. This classifier normally processes the XML files in the
training data which contains various sizes of the board. It classifies the normal images and warning
signs effectively. If found the intended image, it sends the warning signal to the Pi board and further
sends the control signal to the 1293d.

Fig.3. Rectangular Region

In this system, the motor driver IC 1293d is equipped for the efficient control of the DC motors.
More specifically, one driver IC can be able to operate a couple of motors. So, the proposed system
uses one 1293d for process of control in which the input of the GPIO is connected to the driver IC and
the output pin is unite to the motor IC. Also, the system automates the speed of the left wheels and
right wheels to slow down when sign boards are detected. To accomplish the task, GPIO pin (2,3) is
meant for left wheel control and GPIO pin (9,10) is for the right wheel.

4
RASCC 2020 IOP Publishing
Journal of Physics: Conference Series 1717 (2021) 012027 doi:10.1088/1742-6596/1717/1/012027

3.3 Experimental Results

In this proposed system, VNC viewer is linked to the Raspberry Pi for viewing the vehicle status. It
normally connects to the R-Pi using the IP address (Figure 4).

Fig.4 VNC viewer window

After getting authenticated, vehicle status can be viewed in Raspberry Pi B window. Various status
of the vehicle is processed by python and shown in IDLE. For instance, the below figure shows the
distance measure of the vehicle ahead to it.

Fig.5 IDLE window

Figure 6 shows the road side symbol contains the information of speed lowering. The data with the
corresponding label is fetched from the training data set after gets processed by the classifiers.

5
RASCC 2020 IOP Publishing
Journal of Physics: Conference Series 1717 (2021) 012027 doi:10.1088/1742-6596/1717/1/012027

Fig.6 Speed limit symbol

The prototype of the proposed system is shown in figure 7.

Fig.7 Prototype model

4. Conclusion
The proposed system provides a novel framework for automatic speed control of the vehicle using
Raspberry Pi B. Moreover, it establishes a safer transportation system that facilitates both pedestrians
and vehicle users. Open CV and python programming used for automate the vehicle according to the
warning and sign boards. Furthermore, ultrasonic sensors efficiently detect the objects and lowering
the speed of the vehicles if obstacles found. To view the working of the propounded system, VNC
viewer is connected to the microcontroller. The prototype model is designed and tested for various
conditions. Thus, the proposed system offers efficient vehicle automation and speed control in
restricted areas to avoid accidents.

References
[1] Bhavanam, Dr. 2014. Automatic Speed Control and Accident Avoidance Of vehicle using Multi
Sensors, Proceedings of International Conference on Innovations in Electronics and
Communication Engineering.
[2] Francesco Bella, (2011) A Collision Warning System for rear-end collision: a driving simulator
study, Procedia - Social and Behavioral Sciences, Volume 20, Pages 676-686
[3] Muthuramalingam, Sankayya & Bharathi, A. & kumar, S. & Gayathri, N. & Sathiyaraj, R. (2019).
IoT Based Intelligent Transportation System (IoT-ITS) for Global Perspective: A Case Study.
10.1007/978-3-030-04203-5_13.

6
RASCC 2020 IOP Publishing
Journal of Physics: Conference Series 1717 (2021) 012027 doi:10.1088/1742-6596/1717/1/012027

[4] Sumit Mallik, (2014) Intelligent Transportation System, International Journal of Civil Engineering
Research. ISSN 2278-3652 Volume 5, Number 4 pp. 367-372 © Research India Publications.
[5] Anandhalli, Mallikarjun & Baligar, Vishwanath. (2017). A novel approach in real-time vehicle
detection and tracking using Raspberry Pi. Alexandria Engineering Journal. 10.1016/ j.aej.
2017.06.008.
[6] Selvarajah, K. & Tully, A. & Blythe, Philip. (2008). ZigBee for Intelligent Transport System
applications. 1 - 7. 10.1049/ic.2008.0814.
[7] Richardson, Matt, and Shawn P. Wallace.(2015) Make: getting started with Raspberry Pi.
Sebastopol, CA: OReilly.
[8] Molloy, Derek. (2016) Exploring Raspberry Pi: interfacing to the real world with embedded Linux.
Indianapolis, IN: John Wiley & Sons.
[9] Membrey, P., D. Veitch a R. K. C. Chang. (2016) Time to measure the pi. Association for
Computing Machinery. Sponsors: ACM SIGCOMM; ACM SIGMETRICS; Conference code:
124785. ISBN 9781-450345262(ISBN), 327-334.
[10] Naveenkrishna, M. A, S. Jayanthy,(2015) Real time vehicle tracking and monitoring using
International Journal of Applied Engineering Research., vol. 10, no.20, s. 15259-15263.
[11] CH. Madhuri Devi, Atiya Sultana, (2018) Speed regulation using raspberry pi for road sign
recognition system, IRJET, Volume: 05 Issue: 09.
[12] P. A. Shinde and Y. B. Mane, (2015), Advanced vehicle monitoring and tracking system based on
Raspberry Pi, IEEE 9th International Conference on Intelligent Systems and Control (ISCO),
Coimbatore, pp. 1-6, doi: 10.1109/ISCO.2015.7282250.
[13] Nagalaskhmi T S et.al,(2016) Raspberry Pi based Embedded System for Vehicle Automation
over Internet, International Journal of Advanced Research in Computer and Communication
Engineering, Vol. 5, Issue 12.
[14] Z. Chen, X. Hu, Y. Li and Z. Zhang,(2017) Speed control system design of automatic parking
based on fuzzy-PID control, IEEE International Conference on Information and Automation
(ICIA), Macau, 2017, pp. 989-993, doi: 10.1109/ICInfA.2017.8079046.
[15] Sumit Deshpande et.al,(2017 Implementing a system to detect over speeding & inform authorities
in case of any violations, IRJET,Volume: 04 Issue: 04
[16] Shreyash Wankhade et.al, (2017) Smart Screen Using Raspberry Pi, IJEMR, Volume-7, Issue-1.
[17] Varun, Kritika Garg (2016) Face Recognition Using Haar Cascade Classifier", International
Journal of Emerging Technologies and Innovative Research, ISSN: 2349-5162, Vol.3, Issue 12,
page no.140-142.
[18] Bradski G. Kaehler A,(2008), Learning OpenCV – Computer Vision with the OpenCV Library,
O’Reilly Media
[19] Padilla, Rafael & Filho, Cicero & Costa, Marly (2012). Evaluation of Haar Cascade Classifiers
for Face Detection, International Journal of Computer, Electrical, Automation, Control and
Information Engineering Vol:6, No:4.
[20] Lienhart, R., Kuranov, A., Pisarevsky, V., “Empirical Analysis of Detection Cascades of Boosted
Classifiers for Rapid Object Detection”, in 25th Pattern Recognition Symposium (DAGM’03),
pp. 297-304.