11 II February 2023

https://doi.org/10.22214/ijraset.2023.49068
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 11 Issue II Feb 2023- Available at www.ijraset.com

Adaptive Traffic Control System

Vineeta Choudhary1, Shery Tank2, Kriti Gulati3, Shubham Jani4, Bhaumik Machhi5
1, 2, 3, 4
Undergraduate Students, Computer Science and Engineering Parul University
5
Assistant Prof, Computer Science and Engineering Parul University

Abstract: Whenever we hear the word traffic, we all think of people blaring horns and waiting endlessly, stress is always silent
but prominent in the word traffic. We all face traffic daily and have experienced the frustration and stress that traffic induces.
Our project focuses on reducing the traffic waiting time significantly and hence reducing air and noise pollution. Less waiting
time at traffic means less wastage of fuel leading to energy conservation in the times of a global warming.
Keywords: Traffic Monitoring, Intelligent Transport System, ATCS, Image Processing, Traffic Management System, Adaptive
Traffic Control System
I. INTRODUCTION
India a developing country has billions of vehicles on roads and has a never-ending manufacturing of them, minimal infrastructure
to handle traffic leads to congestion especially in a metropolitan city. This congestion leads to traffic that are hours long and cause
inconveniences in the lives of people. Most of the traffic control systems have fixed signal lengths based on time, problems stated
above clearly indicate that a traffic control system that adapts to adversities is needed. Hence Adaptive Traffic Control System
comes in and helps reduce the waiting time at a given traffic. This project was made by a team of computer engineers by using
several technologies for tracing the vehicles and interfacing the output with the input from Arduino via cameras present on traffic
intersections.
II. REVIEW OF LITERATURE
The technologies used for this paper have been previously researched upon for the betterment of the ATCS and platforms related to
the same. Some of their works have been reviewed and observed for further research.

A. A Real Time Density Based Traffic System Control System

Air and traffic pollution, precious fuel wastage and heavy traffic compensations can all be significantly decreased with the use of
smart traffic control systems. This paper gave an insight of how an adaptive traffic control system would revolutionize most of the
adversities we face with traffic in daily life. It gave a detailed insight about making a system which is adaptive using tools like
TensorFlow and OpenCV, Density based control of traffic with the help of machine learning using different algorithms. A system
which is also real time for optimal functioning.

B. A Self-Adaptive Traffic Light Control System Based on YOLO

You only look once is based on real-time object detection relying on a deep Convolutional Neural Networks to function which is a
part of machine learning. YOLO version V3and V4 are discussed in detail with their architecture. Adaptive Traffic Light Algorithm
is mentioned, and this paper further discusses how C02 emissions will be reduced significantly using YOLO algorithm and how it is
still undergoing different phases of testing to be interfaced with hardware efficiency.

C. Real-Time Adaptive Traffic Control System for Smart Cities

The benefits of using smart/adaptive traffic control system are explained. It estimated that by 2025, those cities which will
implement smart traffic control systems they will reduce their commute cycle by 15-20 percent on an average. Architecture of
intelligent transport system is explained. Insights on implementation of Adaptive Traffic Control System is given. The working
includes Video feed acquisition and Pre-processing of video. The conclusion of paper stated the advantages of smart system and
ways to enhance them significantly by using device and sensors which are powered by solar cells.

D. Automation of Traffic Control System Using Morphological Operation

As the traffic related problems are on an all-time high in today’s world, with the help of modern technologies most of them can be
mitigated using Image Processing, Motion Vector Technique (MVT), Radio Frequency and Regression Analysis (RA). The article
talks about all the above-mentioned techniques and tools with the help of which smart traffic control systems can be made and
implemented. The article continues and discusses how the above-mentioned technologies can reduce cost and hardware module.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 495
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 11 Issue II Feb 2023- Available at www.ijraset.com

E. An Optimal Adaptive Traffic Signal Control Algorithm for Intersection Group

This paper gave a detailed mathematical explanation of model for a single intersection which included abstract queue length model,
objective functions and stated the mathematical working of practical queue model. Detailed working of 4 traffic signal control
algorithm for single intersection. The mathematical explanation included two adjacent intersections in Kumming city data from both
the intersection was collected from detector then calculated and estimated. The results showed how the abstract queue length model
reduced waiting time by 10-16%.
III. WORKING

Fig. 1 The Design

The Adaptive traffic control system working is shown in the figure above. There are two main tasks: Input, in the form of image
capture from the cameras present at traffic intersections and second is Output, which will be change in traffic signal timer based on
density detection with the help of tools like OpenCV library SciPy and NumPy libraries. In this project the image attainment is done
by capturing multiple images by cameras present on traffic signals itself, the acquired image is then processed with the help of
algorithm YOLO in python. Density is then calculated from the images processing which uses artificial intelligence and machine
learning. The counter which assigns the time at traffic signal is interfaced such that it updates the time based on density detection,
which will be our output here. In Adaptive Traffic Control System, a prototype was made by us to simulate the project on a smaller
scale, it detects moving toy cars and changes counter time accordingly. We made a website specifically dedicated to our future
clients to post feedbacks and suggestions if required. We choose to make a web-based platform since we didn't want our project to
be limited to a particular platform. The Input part of this project has been made using Python libraries, OpenCV, Machine Learning
and Artificial Learning. The Prototype was made using Arduino, LEDs, Digital Display and a CCTV Camera.
Adaptive Traffic Control System Front-end was made using have been made using HTML, CSS, JavaScript and React,

The following technologies have been utilised for the development of ‘Adaptive Traffic Control System:
1) OpenCV and TensorFlow
2) Python Libraries
a) SciPy
b) NumPy

3) Machine Learning & Artificial Intelligence

a) YOLOv3
b) YOLOv4

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 496
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 11 Issue II Feb 2023- Available at www.ijraset.com

4) Front-end Design
a) JavaScript
b) React
c) HTML
d) CSS

IV. UML DIAGRAMS

Fig. 2 Class Diagram for ATCS

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 497
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 11 Issue II Feb 2023- Available at www.ijraset.com

Fig. 3 Flow diagram of ATCS

V. FUTURE SCOPE
Adaptive Traffic Control System can be improved in the future by
1) Integrating with number plate detection.
2) Thermal Image Processing to improve efficiency.
3) Solar powered detectors to minimize power dependency.
4) Synchronize all traffic squares to improve accuracy.
As time and technology proceeds, Adaptive traffic control system will be making everyone’s life better, from decreasing waiting
time in traffic to reducing noise and air pollution. This theoretically guarantees that Adaptive traffic control system sole purpose to
relieve traffic stress to make our daily life easy.

VI. CONCLUSION
In this age of technology, we still struggle with the daily hassle of being struck in traffic. Contributing to air and noise pollution and
wastage of fuel. All this aggravating climate change and global warming. With Adaptive Traffic Control System, we tried to provide
an extra set of hands in easing the above stated problems and reducing the time we spend being struck in traffic. With the help of
ATCS, there will less traffic waiting time and reduced commute cycles leading to reduced air and noise pollution. Fossil fuel is
being consumed at an alarming rate and our project would also aid in reducing fuel wastage.

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 498
 International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Volume 11 Issue II Feb 2023- Available at www.ijraset.com

VII. ACKNOWLEDGEMENT
An endeavour over a long period of time can be successful with the advice and support of many well-wishers. We take this
opportunity to express our gratitude and appreciation to all of them.
We first take the privilege to thank Dr. Amit Barve, Head of the Department, Computer Science & Engineering PIET for his
valuable support and guidance during the period of project implementation.
We wish to express our sincere and gratitude to our project guide Prof. Bhaumik Machhi, Assistant professor, Department of
Computer Science & engineering, PIET, for the simulating discussions, in analysing problems associated with our project work and
for guiding us throughout the project. Project meetings were highly informative. We express our warm and sincere thanks for the
encouragement, untiring guidance, and the confidence he had shown in us. We are immensely indebted for him valuable guidance
throughout the project.

REFERENCES
[1] ACJK Chandrasekara, RMKT Rathnayaka, and LLG Chathuranga. A real- time density-based traffic signal control system. In 2020 5th International
Conference on Information Technology Research (ICITR), pages 1–6. IEEE, 2020
[2] Prayushi Faldu, Nishant Doshi, and Reema Patel. Real time adaptive traffic control system: a hybrid approach. In 2019 IEEE 4th international conference on
computer and communication systems (ICCCS), pages 697–701. IEEE, 2019
[3] Shyam Shankaran and Logesh Rajendran. Real-time adaptive traffic control system for smart cities. In 2021 International Conference on Computer
Communication and Informatics (ICCCI), pages 1–6. IEEE, 2021
[4] M. H. Tunio, I. Memon, G. A. Mallah, N. A. Shaikh, R. A. Shaikh and Y. Magsi, "Automation of Traffic Control System Using Image Morphological
Operations," 2020 International Conference on Information Science and Communication Technology (ICISCT), Karachi, Pakistan, 2020, pp. 1-4, doi:
10.1109/ICISCT49550.2020.9080051
[5] Wei Cheng, Xiaolan Liu, and Wenfeng Zhang. An optimal adaptive traffic signal control algorithm for intersections group. In 2006 6th World Congress on
Intelligent Control and Automation, volume 2, pages 8683–8686. IEEE, 2006

©IJRASET: All Rights are Reserved | SJ Impact Factor 7.538 | ISRA Journal Impact Factor 7.894 | 499