The Global status report on road safety 2018 launched by WHO in

The Global status report on road safety 2018, launched by WHO in December 2018, highlights that the number of annual road traffic deaths has reached 1.35

million. Road traffic injuries are now the leading killer of people aged 5-29 years.

The burden is disproportionately borne by pedestrians, cyclists and motorcyclists, in

particular those living in developing countries. The report suggests that the price

paid for mobility is too high, especially because proven measures exist. Drastic action is needed to put these measures in place to meet any future global target that

might be set and save lives.

[1] With this a humongous increase in Urban population,

this number of accidents will increase if preventive measures are not get considered

immediately. Jams are not only frustrating, they are also a major contributor to air

pollution, and that’s bad not just for our climate, but everybody’s health too. According to researchers at the Harvard Center for Risk Analysis, congestion in the 83

largest urban areas in the United States caused more than 2,200 premature deaths in

2010 [2] In recent years number of private motor vehicles are rising, due to increase in

their popularity, but increase in number of vehicles on road and no change in width

of roads or building of new roads causes mega traffic blocs in cities.

We are currently

using traditional ways of controlling traffic i.e. with the help of traffic police. Use of

manpower is considered, which is not a bad idea but an idea with more accuracy and

efficiency, the problem is humans have some limits due to their physical and mental

abilities, such as the can’t count number of vehicles, or can’t remember number plates,

can’t take quick decisions with ease and accuracy.

Get quality help now
Doctor Jennifer

Proficient in: Carbon Dioxide

5 (893)

“ Thank you so much for accepting my assignment the night before it was due. I look forward to working with you moving forward ”

+84 relevant experts are online
Hire writer

This and all related problems can

be overcome with the use of IoT and Machine Learning. .

The aim of this paper is to build a suitable model for solving such problems, with



integration of Raspberry Pi, an microcontroller, along with CCTV cameras mounted

on significant places with Image processing algorithms. In previous papers canny

edge detection algorithms was used, the main drawback of this algorithm was it takes

lots of time due to it’s reach computations and it is very complex to be implemented

on real time data. We are using HAAR Cascade algorithm, the main reason behind

it is it’s computation speed, it is faster than Canny edge detection, around 60 microprocessor instructions are required to calculate a 2 rectangular feature.

1.2 Motivation:

We already have some of the very advanced systems to help management of

traffic. Thus, this study is focuses not only on traffic congestion, but also focuses

various other aspects such as emergency vehicle rescue, culprit catching etc. Due to

traffic jams in urban city, the main problem occurs is emergency vehicles can’t get

the path, this happens due to 2 reasons first is the width of road and other one is

pure management of traffic. The CCTV camera mounted on signals used for traffic

surveillance can be used for various other purposes such as number plate identification

and culprit catching.

Several ways can be used to manage traffic, we are primarily working on IoT

integration with Machine Learning to understand traffic patterns, extraction of knowledge from the same, and future prediction of traffic patterns to help drivers finding

optimal route.

1.3 Objectives:

• This system will firstly gather all necessary data from CCTV cameras and

analyze it with the help of modern high processing servers with the help of

cloud in real time.

• This derived knowledge is then used accordingly for monitoring traffic, scheduling traffic signals, identification of emergency and other (culprit) vehicles.

• The proposed system focuses on reducing traffic and prevention of congestion.


SVIT,Nashik, Department of Information Technology Engineering – 2019

Chapter 2


2.1 Literature Survey:

Traffic congestion is a major problem in many cities, main reason is increased interest in buying private vehicles, less wide roads and management

failures. Traffic management is currently handled by human resource with the

help of traffic police and CCTV camera mounted on significant places for surveillance. This surveillance is carried out manually by humans sitting in control

station. The main defect in human resource use is it’s lack in efficiency and

effectiveness. Many people tried may solutions using IoT and Machine learning

to tackle this problems.

2.1.1 Paper Title:” Automated Traffic Monitoring Using Image Vision”[3]


R. Krishnamoorthy, Sethu Manickam et al


The process of traffic monitoring is predominantly carried out manually in our

country. Traffic monitoring encompasses a set of stringent rules to be followed while

ensuring that there are no traffic jams at the juncture of roads. In this paper, a

novel method is proposed to automate the traffic signal lights with the assistance

of multiple CCTV cameras connected over the Internet to survey various roads at

the junction. The process comprises two primary phases: Vehicle Detection System

and Traffic Scheduling Algorithm. Vehicle Detection shall be carried out in Digital



Image Processing (DIP) by applying a simple kernel-based Edge Detection in Spatial

Domain followed by an algorithm to detect the perimeter of closed figures while simultaneously applying the concepts of Machine Learning to classify the vehicle type

into the following categories of motorcycle, light motor vehicle, and heavy motor vehicle. Subsequent processes are carried out in a novel Traffic Scheduling Algorithm

through the help of a hybrid Round Robin having a dynamic time slice obtained by

using Longest Remaining Job First to periodically update the traffic signal lights to

relax the traffic. Instead of turning on the green light for a fixed amount of time, the

duration will be managed dynamically based on the amount of traffic in each road.

Thus, the proposed system is aimed at reducing the jamming of roads by a huge



In this paper the proposed system it consist of mainly two parts, vehicle detection

and traffic scheduling. This uses CCTV camera mounted on traffic signals along

with Dip Image processing by applying kernel based edge detection using Canny

edge detection algorithm to identify close figures and modify traffic signal timings.

Simultaneously applying Machine Learning to classify between various types of traffic

vehicles, and round robin algorithm to schedule traffic lights


By using Canny edge detection algorithm for close figure identification makes this

model a bit complex, the reason behind it is Canny edge detection is very slow due

to it’s complex calculations and it is a bit difficult to apply on real time traffic data.

2.1.2 Paper title: “IoT based smart traffic signal monitoring system using

vehicles counts” [4]


Senthil Kumar Janahan, Veeramanickam Murugappan, Kumar Narayanan et al


SVIT,Nashik, Department of Information Technology Engineering – 2019



Traffic signal management is one of the major problematic issues in the current

situation. Such scenarios, every signal are getting 60 seconds of timing on the road

at a regular interval, even when traffic on that particular road is dense. As per this

proposed model in this article, which will be optimized the timing interval of the

traffic signal purely depends on the number of vehicles on that particular roadside.

The major advantage of this system is that it can able to decrease the more waiting

time for the drivers to cross road signal. In this model, we are using the clustering

algorithms model which is based on KNN algorithm. Using this algorithm new model

will be liable to determine expected required timing as per provided inputs to the

signal which is vehicles count. The input of these systems is vehicles counts on each

side of the road from crossing signal. And this input will be determined on much

time is to be provided. “Case studies on this system are traffic network and real-time

traffic sub-networks are organized to get the effectiveness of the proposed model.”


The paper has an objective of reducing traffic signal waiting time with IoT

approach. It uses IR Motion sensor for detecting motion of vehicles along with a

road, it uses simple sender receiver sensors. Using IR Motion sensors it draws a line

using sender and receiver i.e. sender sends an laser signal which is mounted on one side

of road, and the receiver sensor which captures that signal mounted on another side

of road, it causes an laser line, whenever any vehicle crosses that line a disturbance is

made which causes the processor to make a count of vehicle, which apparently used

to detect density of traffic


The main drawback of system proposed in this paper is it’s IR sensor itself, it

counts vehicles when disturbance is made across sender and receiver, as if more than

2 vehicles are crossing laser line simultaneously sensor will count that as a single interuption and a single vehicle which is false in itself, apparently other obstacles such

as pedestrians, animals can also cause similar kind of obstruction and false reading.


SVIT,Nashik, Department of Information Technology Engineering – 2019


Alongside of this, system proposed in this paper is not sufficient to identify or classify

between vehicle types.

2.1.3 Paper title, “IoT Based Traffic Management System”[5]


Mahesh Lakshminarasimhan et al


In the contemporary world, urban mobility is one of the unprecedented challenges to be tackled in the administration of a big city. This paper analyses the ever

growing urban population around the globe and discusses about the traffic systems

in densely populated cities like Los Angeles and Amsterdam. Further, an advanced

traffic management system is proposed, implemented using Internet of Things (IoT).

The system is supported by a circuit embedded in the vehicle, which operates using

RFID with clustered systems. The functionalities of the system include efficient traffic light control, parking space identification and anti-theft security mechanism. The

proposed architecture and working with big data analytics involving Hadoop is presented. Moreover, supervised learning methodologies are proposed that would help

in determining the standard of roads, estimating overall traffic flow, calculating average speed of distinct vehicle types on a road and analyzing the travel path of a vehicle.


The work in this paper is based on an mechanism installed on vehicles for

detecting it’s local positions on road, it uses RFID for the same instead of GPS,

RFID will interact with nearby substations mounted on road junctions for their real

time local position analysis, this RFID mechanism can be interacted manually or

automatically with mobile applications. An IR sensor is installed on roads along with

substations which will use to communicate with local servers and vehicles for their

positions. This real time positions are then use to analyze density of traffic on road



SVIT,Nashik, Department of Information Technology Engineering – 2019



By using RFID, IR sensors along with local substations for local position analysis of vehicles mainly takes lots of time for calculations. Paper suggests that RFID

Mechanisms has to installed on each and every vehicle for working of this model, this

is practically more challenging. Mounting substations across a numerous cities or a

country along with installation of IR sensing system integrated to worm with those

substations will be money and time consuming.

2.1.4 Paper title: “Prevention of Air Suffocation inside a Car Cabin Using a Mechatronic System“[4]


Rajendra Prasad et al.


Loss of life inside an enclosed car cabin due to the suffocation though rare but it

is evident and phenomenal all these days. Inside a closed space or cabin, People inhale

their own exhaled air that carries a greater proportion of carbon dioxide (CO2). In

addition to this, the case of oxygen gas getting depleted leads to further increase of

suffocation. So in order to help people, infants, pets who/which get caught in these

unavoidable and unexpected situations, this project gives a solution that may prevent

people from reaching fatal situations. A simple concept of air diffusion from region

of higher concentration to lower concentration is used here. The theme of the project

is to detect the critical suffocating level of CO2 and prevent suffocation by automatically controlling the power windows of the car to shut open, thereby allowing fresh

air to come inside the car cabin and avoiding suffocation. In this project a cubical

glass tank as a substitute for car cabin and carbon dioxide cylinder as a source of

CO2 for our experimental purpose and convenience. Here gas sensors are used to

sense the level of CO2, the sensor gives the signal to Arduino UNO chip. Arduino

sends signal to the DC motor of the power window. The entire setup is run by a

12V battery. Once the DC motor receives the signal from Arduino, it runs and pulls

the window down. In real life application the sensor and controller are replaced by a


SVIT,Nashik, Department of Information Technology Engineering – 2019


printed circuit board which comes as a part of the car management system.


The paper work on gas sensors which sense the CO2, the sensor gives the signal

Cite this page

The Global status report on road safety 2018 launched by WHO in. (2019, Dec 18). Retrieved from

Let’s chat?  We're online 24/7