Internet Of Things (CSE-3024)

Smart Parking System using Raspberry Pi

Name of the faculty: Prof. Parveen Sultana

Submitted by:

17BCE0168 Sidarth Wadhwa

17BCE0243 Ritwik Singh

17BCE0343 Tanishq Wadhwani

 Acknowledgment
We are thankful to our faculty Prof. Parveen Sultana H
for giving us this opportunity to work on this project by
guiding us throughout the project and we are highly
obliged to receive her precious suggestions and advice.

Sidarth Wadhwa- 17BCE0168

Ritwik Singh - 17BCE0243

Tanishq Wadhwani- 17BCE0343

Contents:
1. Abstract

2. Introduction

3. Literature review

4. Objectives

5. Parts used

6. Sensors used

7. Intro to software used

8. Work flow

9. Architecture diagram

10. Code snippet

11. Output

12. Conclusion
Abstract:
This project aims upon creating an automated parking lot where the cars are allowed
parking spots on the basis of their license plate numbers. Instead of traditional
methods such as the usage of RFID, we would be using OpenALPR to process the
data on cloud to achieve better performance by taking off most of the computational
load from Raspberry Pi. Without the use of RFID tags, we would make it economical
as well.

Introduction:
Our project aims to create an automated parking lot where cars are registered for
parking spots based on their license plate numbers. The license plates are captured by
a camera fitted near the entrance to the parking lot. This data is then sent to the
Raspberry Pi. The Pi processes this image by using an external, web-based API,
OpenALPR.
OpenALPR has a cloud based API that is used to process the data. This helps remove
potential processing load from the Pi, which does not have a high power CPU, thus
allowing us to execute complex algorithms on the Pi. The API recognises the number
plate using its algorithms and returns the plate number hence extracted. The number
is then used to allot a parking spot to the car.

When the car reaches the exit, it is removed from the spot list and the spot is then
indicated as being empty, free to be allocated to other cars.

Literature Review:
Rocha, A., Souza, A., Johnathan, D., Aquino, G., Queiroz, R., & Melo, M. (2019, July).
Evaluating ThingSpeak as an IoT Event Platform on building a Smart Parking Application.
In Anais do XI Simpósio Brasileiro de Computação Ubíqua e Pervasiva e II Workshop
Brasileiro de Cidades Inteligentes. SBC.

This paper concerns itself with the application of a smart parking system that utilises RFID with a
Raspberry Pi, and ThingSpeak as the cloud service.

Li, Y., & Lin, G. (2019, April). Design of intelligent parking lot based on Arduino. In IOP
Conference Series: Materials Science and Engineering (Vol. 490, No. 4, p. 042010). IOP
Publishing.

This paper first discusses the problems posed by the parking systems used traditionally: barriers
cause congestion while scratch type tickets need to be updated regularly. It also brings power
consumption into the scope of the discussion, discussing figures relating to electricity consumption
by big cities, and highlighting the power efficiency (and capability to run on modest amounts of
green energy) of IoT applications.

Authenticated IoT Based Online Smart Parking System with Cloud

Kuchi NSSSS Utpala, N Suresh Kumar, K Praneetha, D Hema Sruthi, K Sai Avinash Varma
Pramana Research Journal 9 (4), 2019

The objective of this project is to build an online parking slot booking. And also secure it with
various security algorithms to protect it from intruders.

Smart Parking—A Wireless Sensor Networks Application Using IoT

Suman Balhwan, Deepali Gupta, SRN Reddy
Proceedings of 2nd International Conference on Communication, Computing and
Networking, 217-230, 2019

The paper talks about the growth of Internet of Things and Cloud technologies have give rise to
new possibilities in terms of smart cities. Smart parking facilities and traffic management systems
have always been at the core of constructing smart cities.

Alsbou N., Afify M., Ali I. (2019) Cloud-Based IoT Smart Parking System for Minimum
Parking Delays on Campus. In: Issarny V., Palanisamy B., Zhang LJ. (eds) Internet of Things
– ICIOT 2019. ICIOT 2019. Lecture Notes in Computer Science, vol 11519. Springer, Cham

Growing cities always have parking challenges and they are in need for creative ideas to solve this
issue and avoid the time wasted in searching for empty parking spots. To overcome the problem,
this paper proposes a simple solution using a low-cost cloud-based system design.

Neha Malkar, Pranali Taklikar, Manish Borkar, Sushant Pogale, Kamlakar Sonkusare, Prof.
Rubana Khan, "Survey Paper on An IoT Based Smart Parking System", International
Journal of Scientific Research in Computer Science, Engineering and Information
Technology (IJSRCSEIT), ISSN : 2456-3307, Volume 5, Issue 2, pp.633-635, March-April-
2019.

In this study a Smart Parking System (SPS) is planned which enables the user to find the nearest
parking area and gives availability of parking slots in that respective parking area. It mainly
concentrates on reducing the time in finding the parking area and also it avoids the unnecessary
travelling through filled parking areas in a parking area. Thus it decreases the fuel consumption
which in turn reduces carbon footprints in an atmosphere.

Objective:
We aim to create a smart parking management system that identifies the vehicles accessing
the parking spaces using a license plate recognition algorithm (OpenALPR).

Parts used:
• Raspberry Pi
• Pi Cam or USB webcam
• MicroSD card
• Ultrasonic Sensor
• LEDs
• Resistor - 220 ohms
• Breadboard
• Jumper wires

Sensors Used:
• Ultrasonic sensor- It is used to detect the presence of a car. Once a car’s presence is
detected, the camera is activated to take a picture.
• Camera- Used to take a picture of the cars attempting to use the parking space. An
image is taken to identify them uniquely using license plate recognition.

Intro to Software Used:

OpenALPR is an open source Automatic License Plate Recognition library written in
C++ with bindings in C#, Java, Node.js, Go, and Python. They also have
the OpenALPR Cloud API which is a web service running in the cloud that analyzes
images of vehicles and responds with license plate, model, color and much more.
OpenALPR Cloud API has a free service that allows up to 2000 free recognitions per
month
Workflow:
1. We will use the camera to capture an image of the car.
2. The image is then sent to the OpenALPR portal for processing.
3. The portal runs its plate recognition algorithm on the image to segment and read
the license plate.
4. The output is then sent back to the microprocessor.
5. The number thus obtained is used to uniquely identify the car instead of using
RFID.
The car is allotted a space based on the available spaces. Once a car leaves, it is
checked out and the parking space status is changed to free. New cars can then access
that space as and when required.

Architecture diagram:
Ultrasonic sensor
Pi camera

Code
import pandas as pd
data = [0,0,0,0,0,0,0,0,0,0]
index = [1,2,3,4,5,6,7,8,9,10]
s = pd.Series(data,index)

p = 1
if p == 1:
np = str(input("Number plate: "))
j=0
for i in s:
j+=1
if i==0:
print(j)
s.update(pd.Series([np], index = [j]))
break

p = 1
if p == 1:
np = str(input("Number plate: "))
j=0
for i in s:
j+=1
if i==0:
print(j)
 s.update(pd.Series([np], index = [j]))
break

p = 1
if p == 1:
np = str(input("Number plate: "))
j=0
for i in s:
j+=1
if i==0:
print(j)
s.update(pd.Series([np], index = [j]))
break

p = 1
if p == 1:
np = str(input("Number plate: "))
j=0
for i in s:
j+=1
if i==0:
print(j)
s.update(pd.Series([np], index = [j]))
break

p = 1
if p == 1:
np = str(input("Number plate: "))
j=0
for i in s:
j+=1
if i==0:
print(j)
s.update(pd.Series([np], index = [j]))
break

print(s)

q = 1
if q == 1:
nq = str(input("Number plate: "))
j=0
for i in s:
j+=1
if i==nq:
print(j)
s.update(pd.Series([0], index = [j]))
break

print(s)
p = 1
if p == 1:
np = str(input("Number plate: "))
j=0
for i in s:
j+=1
if i==0:
print(j)
s.update(pd.Series([np], index = [j]))
break

print(s)

Implementation

Circuit

Node-RED Implementation screenshot

Output
PS C:\Users\wadhw\Personal Storage\Workspace\IOT Project> python logic.py
Number plate: MP01
1
Number plate: MP02
2
Number plate: MP03
3
Number plate: MP04
4
Number plate: MP05
5
1 MP01
2 MP02
3 MP03
4 MP04
5 MP05
6 0
7 0
8 0
9 0
10 0
dtype: object
Number plate: MP03
3
1 MP01
2 MP02
3 0
4 MP04
5 MP05
6 0
7 0
8 0
9 0
10 0
dtype: object
Number plate: MP06
3
1 MP01
2 MP02
3 MP06
4 MP04
5 MP05
6 0
7 0
8 0
9 0
10 0
dtype: object

Results and Conclusion:

This was a learning experience for us, as we were introduced to new technologies
(interfacing with Pi camera) and new APIs (OpenALPR). We believe this project will
improve the efficiency and functionality of vehicle parking spaces. As stated in our
literature review, we found many comprehensive studies that solidified this fact.
Faster processing helps reduce waiting times, which is the reason why we decided to
use an external API for this purpose.
We believe this experience will help increase our familiarity with the working of
embedded systems and the Internet of Things, and are thankful for the opportunity.