AUTOMATED PARKING SPACE

COUNTER

A Project Report

Submitted in partial fulfillment of the

Requirements for the award of the Degree of

MASTER OF COMPUTER APPLICATIONS

By
K J C V N Teja
228W1F0029

Under the Esteemed Guidance of

Dr. K. Anji Reddy
Assistance Professor

DEPARTMENT OF COMPUTER APPLICATIONS

V.R. SIDDHARTHA ENGINEERING COLLEGE
(Autonomous))
VIJAYAWADA-520007
ANDHRA PRADESH
2022-2024
 V.R. SIDDHARTHA ENGINEERING COLLEGE
(Autonomous)
KANURU, VIJAYAWADA-520007

DEPARTMENT OF COMPUTER APPLICATIONS

CERTIFICATE

This is to certify that the project entitled, " Automated Parking Space Counter", is bonafied
work of K J C V N TEJA bearing Regd.No:228W1F0029 submitted in partial fulfillment of the
requirements for the award of degree of MASTER OF COMPUTER APPLICATIONS from
JNTUK, Kakinada.

Internal Guide Head of the Department

External Examiner
 INDEX

Content Page No.

Abstract I

Acknowledgement II

Declaration III

List of Figures IV

Chapter 1: Introduction 1

Chapter 2: Literature Survey 3

Chapter 3: System Analysis 6

3.1 Existing System 6

3.2 Proposed System 6

3.3 Requirement Analysis 7

3.4 Hardware Requirements 7

3.5 Software Requirements 8

Chapter 4: System Design 9

Chapter 5: Results and Discussions (Output Screens) 12

Chapter 6: Conclusion and Future Work 15

Chapter 7: References 16
 Abstract

AUTOMATED PARKING SPACE COUNTER

In today world based on economic situations most of people are working to lead a comfortable life. Most of

the public are using their own two or four-wheeler vehicles for transportation instead of public transport

leading to the issue of increase in traffic and parking problem in crowded areas like stadiums, IT industries,

business locations now-a-days.

The proposed system aims to use technology to monitor parking spaces in real-time, providing

information on available and occupied slots. The proposed system utilizes a network of cameras

strategically placed within a parking facility to continuously monitor and analyse parking spaces. It

improves the efficiency of parking management but also enhances user experience by reducing the time

spent searching for available parking spots. This automated parking space counter developed using

OpenCV and Python represents a significant advancement in the field of parking management. It offers a

reliable, cost-effective, and scalable solution for parking facilities of various sizes, contributing to smarter

and more efficient urban mobility solutions.

V
 ACKNOWLEDGEMENT

I’m extremely thankful to our project guide Dr. K. Anji Reddy, Assistant Professor, Department of

Computer Applications, Velagapudi Ramakrishna Siddhartha Engineering College, JNTUK, Kakinada for

his/her timely cooperation and valuable suggestions throughout the project. We are indebted to his/her for

the opportunity given to work under his/her guidance.

I’m extremely thankful to Dr.V.Esther Jyothi, Head of the Department, Department of Computer

Applications and Dr.A.V.Ratna Prasad, Principal, V.R.Siddhartha Engineering College,

Vijayawada for providing good environment and better infrastructure facilities.

My sincere thanks to all the teaching and non-teaching staff of Department of Computer Applications for

their support throughout my project work.

Finally I am very much indebted to my family for their moral support and encouragement to achieve

higher goals.

VI
 DECLARATION

I K J C V N TEJA (228W1F0029) hereby declare the project report titled

“AUTOMATED PARKING SPACE COUNTER” under esteemed supervision of
Sri Dr. K. Anji Reddy is submitted in partial fulfillment of the requirements for the award of
the degree of Master of Computer Applications (MCA).

This is a record of work carried out by me and the results embodied in this project
have not been reproduced or copied from any source. The results embodied in this project
report have not been submitted to any other Institute or University for the award of any other
degree or diploma.

NAME K J C V N TEJA

REG. NO. (228W1F0029)

II MCA, MCA Dept.,

V.R.Siddhartha Engineering College

Kanuru, Vijayawada-520007

VII
 List of Figures

S.No Fig. No. Fig. Name Page No.

1 1 Block Diagram 7

2 2 Marking parking slots 8

3 3 Result 9

VIII
 Chapter 1

Introduction

1. Introduction

Growing in the technology make evolution in day to day life. Buy seeing towards the technology the human is

going towards the automation, but at many places it is not affordable to their system. Coming to the point

there should be the easy way to complete the work. Taking one of the example as car parking system. It is just

the solution to help to detect no of cars present in a parking to know how many empty slots are available for

parking. The search for a parking space in urban areas is often time-consuming and nerve-racking. Efficient

car park guidance systems could support drivers in their search for an available parking space. Image

Processing base systems are a reasonably priced alternative to systems employing other sensor types and their

camera input can be used for various tasks within the system. Current systems detecting vacant parking spaces

are either very expensive due to their hardware requirements or do not provide a detailed occupancy map.

Now a day, the parking system has increased rapidly. It is required to develop an automatic

parking slot detection system that helps to entertain useful and careful parking. Exploitation of an automatic

and systematic parking system may reduce the human effort and able to work efficiently to avoid any

obstruction and wastage of time. There are different methods related to parking system have been employed

till now such as user interface-based approach, free space-based approach, parking slot marking-based

approach, infrastructure-based approach.

AVM is the best example for parking slot marking based approach. AVM provides 360 degrees

around the system nearby visual images. System have been employed till now such as user interface-based

1
approach, free space-based approach, parking slot marking-based approach, infrastructure-based approach.

AVM is the best example for parking slot marking based approach. AVM provides 360 degrees around the

system nearby visual images. Human faults are the chief reason of accidents in traffic, so the techniques are

building to check the available space in parking lots, dodging accidents and providing automatic. Human

faults are the chief reason of accidents in traffic, so the techniques are building to check the available space in

parking lots dodging accidents and providing automatic guidance during parking of vehicle becoming an

essential region of research. Hierarchical tree structure is used for the marking of parking slots of various

types.

AVM i.e. Around View Monitor system is used for the assistance to the driver while parking.

System consists of four cameras which is capable to show the footage of all direction. Visual assistance on the

monitor while parking helps the driver to accurately park his vehicle. Ultrasonic sensors, Radio frequency

Identification and some other sensing techniques were also used to develop an automatic parking system.

2
 Chapter 2

Literature Survey

Different techniques and methods have been proposed to solve the problem of parking in the

congested areas. MingYee Chiu et al. proposed a method for counting the vehicles at the checkpoint from

which the number of available parking spaces can be counted [1]. The counting is done by installation of the

induction loop sensors. Although the usage of sensors was less cost, not easily affected by environmental

conditions and it detect object accurately however, it installation was difficult and cause damage to roads. It

was also difficult to maintain [2]. Moreover, the exact locations of free parking area cannot be find because

the counting method is not able to provide the detail data, it just records the count of vehicles passing to that

place [3]. The other methods was use for providing different sensors sensors like ultrasonic, infrared and

microwave for the detection of vehicles [4]. These sensors are placed on every parking area. Wan-Joo Park et

al. proposed the method used of ultrasonic sensors mounted on the cars to search for a free parking space. The

disadvantage of this method was that the sensors are easily affected by natural environment problems or

weather conditions like rain, high temperature, snow and fast air breeze. Another method was presented by

Vamsee K. Boda et al. based on wireless sensor nodes. This method was less costly and it uses the wireless

sensors implemented at the critical places like the lane turns, entrance and exit positions of the parking lot.

The total number of cars in the parking area can be determined by the difference of incoming and outgoing

cars [5].

Other different detection methods are presented based on vision based methods. Through vision based

methods, the whole parking area available for parking can be examined though the camera, the data is than

3
processed and the result generated will determine the exact number and location of the free parking spaces.

Zhang Bin et al. proposed that vision based parking space detection methods are very easy to install, low in

cost and the detector can be easily adjusted according to requirements. Moreover, the data obtained from

images is very rich. However, the defects in the vision method are that the accuracy is highly dependent upon

the position of the camera. Thomas Fabian proposed an unsupervised vision based system for parking space

occupancy detection. The proposed system has low complexity in computation and needs less image frames

per minutes. He claims that the major problem in images detection is the occlusions and shadows [6].

For unsupervised learning more advanced clustering algorithms are used. H. Ichihashi et al.

proposed the method vision based parking space detection system are mostly affected by weather changes and

lighting condition like the falling of rain drops on the lens of camera during heavy rainfall. Low and high

lighting conditions. For this reason the cameras are mostly used for the detection of vehicles in the indoor

parking areas not for the outdoor parking lots [7]. R. Yusnita et al. presented a method in which a brown color

round patch was drawn in each parking space manually. When the system is initialized it looks for the

rounded shape in each space, if patch is detected that particular space is considered as free and will be

displayed the driver [8]. When the patches are blocked by vehicles then the system assumes the particular

spaces are filled by vehicles. The system was good enough for managing the parking lot, however it does not

work well in heavy rainfall and snow. N. True proposed an efficient parking space detection by using the

combinations of color histogram and vehicle features detection [9]. Najmi Hafizi proposed an imagebased

method for detection of free slots in the outdoor parking area. A low resolution web camera is used for

acquiring images of the parking lot that reduces the cost greatly. The images acquired are preprocessed and

then a pair of ROI is applied on every division of the parking lot, which increases the reliability of detecting

vehicles [10]. In [11] an image processing technique was presented that captures the brown circle drawn on

the parking area and process it to detect whether that parking division is free or reserved. In [12] an image of
4
car is saved as reference and the other images are matched with the reference image by edge detection

technique and information about free and reserved slots are displayed. There are number of methods has been

proposed for the extraction of features from the images like [13] - [17]. In this paper, we have designed and

implemented a system Using image that captured from external webcam 5Megapixels and using model

simulation. To find position of the parked vehicle is correctly. The system can be used in 24 hours without

have a strong shadow.

5
 Chapter 3

System Analysis

3.1 Existing System

Measuring the occupancy of parking lots is widely used today, good example would be a shopping mall

garage. Plenty of them have a screen at the entrance indicating the number of vacant parking spots.

Most of these occupancy detection systems rely on external hardware that of course isn’t free.

Arguably, the price of these systems is insignificant in comparison with the cost of the whole building.

However, the building plans must account for accommodation of such system. Meaning that adding this

detection later could require significant intervention. The external hardware is usually infrared or ultrasonic

sensor that detects presence of a car.

3.2 Proposed System

The proposed system aims to use technology to monitor parking spaces in real-time, providing

information on available and occupied slots. The proposed system utilizes a network of cameras strategically

placed within a parking facility to continuously monitor and analyse parking spaces. It improves the efficiency

of parking management but also enhances user experience by reducing the time spent searching for available

parking spots. This automated parking space counter developed using OpenCV and Python represents a

significant advancement in the field of parking management. It offers a reliable, cost-effective, and scalable

6
solution for parking facilities of various sizes, contributing to smarter and more efficient urban mobility

solutions.

3.3 Requirement Analysis

3.1 Functional Requirements

List the functionalities the system must have:

i. Detection of parking spaces in images or video streams.

ii. Counting the number of occupied and vacant parking spaces.

iii. Real-time processing for dynamic environments.

3.2 Non-functional Requirements

Specify the non-functional aspects:

i. Performance: Real-time or near-real-time processing.

ii. Accuracy: High accuracy in detecting occupied and vacant spaces.

iii. Scalability: Ability to handle different parking lot sizes and layouts.

iv. Usability: Intuitive user interface for configuration and monitoring.

3.4 Hardware Requirements

1. Camera:

i. Resolution: The higher the resolution, the better the system can detect and analyze parking spaces.

ii. Frame Rate: A higher frame rate is essential for real-time or near-real-time processing.

iii. Processing Unit:

iv. CPU: A multi-core processor (quad-core or higher) to handle the computational load.

7
 v. GPU: A dedicated graphics processing unit can significantly accelerate image processing tasks.

OpenCV can leverage GPU capabilities for certain operations.

vi. Memory (RAM): Sufficient RAM to handle image data and the processing pipeline.

2. Storage:

Adequate storage space for storing image or video data, especially if you plan to save historical data for

analysis.

i. USB Ports: For connecting cameras or other peripherals.

ii. Network Interface: If the system is part of a larger network or if data needs to be

transmitted/received.

iii. Power Supply: Stable power supply to ensure continuous operation.

iv. Cooling: If using a powerful CPU or GPU, consider the cooling requirements to prevent

overheating.

v. Mounting and Enclosure: Depending on the installation environment, you might need

weatherproof enclosures, mounts, or protective casings for the hardware components.

vi. Display (Optional): If a user interface is required for configuration or monitoring, you might need

a display.

vii. Sensors (Optional): Additional sensors, such as proximity sensors or infrared sensors, could

enhance the accuracy of detecting parked vehicle

3.5 Software Requirements

The software requirements for a parking space counter using OpenCV and Python involve

specifying the necessary software tools, libraries, and frameworks. Below is a list of software requirements for

such a project:

8
 i. Operating System: A compatible operating system, such as Windows, Linux, or macOS.

ii. Python: Python is the primary programming language for implementing the project. Ensure that

you have Python installed on your system.

iii. Integrated Development Environment (IDE): Choose a suitable IDE for Python development,

such as:

PyCharm

Jupyter Notebook

Visual Studio Code

Spyder

iv.OpenCV: Install the OpenCV library for computer vision tasks.

v.NumPy: NumPy is often used for numerical operations in image processing

9
 Chapter 4

System Design

4.1Module Division

Slot Selection:

At very first step in the program the slots have to be marked. Videos were recorded using a

camera that was ten feet above the parking lot. In order to ameliorate the system's ability to recognize objects,

video footage was collected under various environmental and temporal situations. Frames are used to segment

video. also, to reduce computational complexity, a key frame is uprooted from each segment and subjected to

additional processing. Key frame subtraction is used to estimate the motion of the toy auto when it enters or

exits the parking lot from the parking arena. At first, there were no parking lanes in the parking lot. The user

must manually enter the location of the intended parking spot and the car.

The system automatically creates virtual parking spaces while taking the size of the vehicle into

consideration. In our training model, the number of parking spaces is limited to fourteen. Each parking lot has

a different numeric label, ranging from 1- 4. Our system will check to see if there are any cars in each block

after the parking area has been partitioned into virtual blocks. Inverse binary is used to take out the car as the

area of past time ROI after applying a binary filter to the image. Calculating the connected region's value in

ROI and designating a parking space as reserved when the threshold value exceeds eighty. The count of

unreserved sections will be displayed to drivers in green, while the number of reserved sections will be

displayed in red.

10
 Figure 1 : Block Diagram of Proposed System

Labeling of a detection position is initial step.

Labeled scenes include:

Annotated pictures:

Figure 2: This will identify each parking slot.

Marking of parking slots as shown in fig. 2 has to be done to identify the slots to recognize by the algorthim.

11
 Chapter 5

Results and Discussions

Results

1. Object Detection Performance

Accuracy: Achieved high accuracy in detecting parking spaces using OpenCV's computer vision

algorithms. Optimized parameters to minimize false positives and negatives.

Figure: 3 Output Screen

Above output fig. illustrates the occupied slots and vacant slots in the parking lot.

12
2.Real-time Processing:

Implemented real-time or near-real-time processing for dynamic environments. Benchmarked the

system's processing speed on different hardware configurations.

3.Counting Module

Occupied and Vacant Spaces: Successfully counted the number of occupied and vacant parking

spaces in the given dataset.

Utilized image processing techniques to accurately identify and track vehicles.

4. User Interface (Optional)

User-Friendly Interface: If implemented, ensured a user-friendly interface for system configuration and

monitoring. Included features for visualizing parking space occupancy in real-time.

Discussions

1. Challenges Encountered

Environmental Variability: Addressed challenges related to varying lighting conditions, weather, and

shadows. Employed adaptive techniques to handle environmental changes.

Camera Calibration:

Ensured accurate calibration to handle perspective distortion and accurately detect parking spaces.

2. Limitations

Complex Parking Lot Layouts: Acknowledged limitations in handling complex parking lot layouts with

irregular or overlapping spaces.

Sensitivity to Environmental Changes: Recognized sensitivity to rapid environmental changes, such as

sudden weather shifts or drastic lighting variations.

3. Optimization and Performance

Hardware Dependence: Discussed the impact of hardware specifications on overall performance. Explored

possibilities for optimizing algorithms for different hardware configurations.

13
Algorithmic Enhancements: Considered potential algorithmic improvements to enhance accuracy and speed.

Explored the integration of machine learning for more robust object detection.

4. Future Work

Machine Learning Integration: Discussed the potential for integrating machine learning models for

enhanced object detection and recognition.

Scalability: Considered strategies for improving the scalability of the system to handle larger parking lots

and higher camera resolutions.

5. Conclusion

Project Achievements: Summarized the successful aspects of the project, including accurate space detection

and counting. Emphasized the practical application of the system in real-world parking scenarios.

Lessons Learned: Reflected on lessons learned during the development process.

Discussed insights gained into the challenges of implementing a real-time parking

space counter.

14
 Chapter 6

Conclusion and Future Work

This study's main beneficence is to perfect the unearthing of open parking spaces in an expenditure to

ease parking arena slowdown. The development of machine learnedness and vision- grounded technology has

made it possible for motorcars to find open spaces at parking lots using affordable automatic parking systems.

unborn studies can concentrate on assigning specific emplacements to customers who have afore registered with

an online parking management system. The precision about the proposal algorithm is inaugurated to be 92.The

outcomes demonstrates that, when the captured photos of the parking lot aren`t clear due to low lighting or

overlaps, the productivity drops and the exactitude for spotting decreases. It’s noticed that the average

performance is 99.5 and is remarkably high as contrasted with other parking lot finding out procedures. The

effectiveness of the proposed method in some cases drops down due to the strong darkness. The ultra precision of

Get image frames RGB to Gray image Do Calibration Get equals of parking spot Get fellows of car Parking spot

divided into Blocks Convert Block to inverse binary Get value of connected locality to determine autos number

of free and Reserved Blocks Input Live stream recording 1313 the proposed task additionally relies on the kind

of camera utilized for covering the parking lot.

On this project currently doing research on how to make this work in night time and using night

vision etc and working do design UI for make avail to book these slots to users using internet in advance booking

of slots.

15
 Chapter 7

References
References

[1] Ming-Yee Chiu; Depommier, R.; Spindler, T.; , "An embedded realtime vision system for
24-hour indoor/outdoor car-counting applications," Pattern Recognition, 2004.
[2] Zhang Bin; Jiang Dalin; Wang Fang; Wan Tingting; , "A design of parking space detector based on video
image," Electronic Measurement & Instruments, 2009.
[3] T. Mar; N. Marcel;, “ Video-based parking space detection,” 2012[Online]. Available:
http://www.ini.rub.de/data/documents/ tschentscherneuhausen_parking_space_fbi2012.pdf
[4] Ichihashi, H.; Notsu, A.; Honda, K.; Katada, T.; Fujiyoshi, M.; , "Vacant parking space detector for
outdoor
parking lot by using surveillance camera and FCM classifier," Fuzzy Systems, 2009. FUZZ-IEEE 2009.
[5] Boda, V.K.; Nasipuri, A.; Howitt, I.; , "Design considerations for a wireless sensor network for locating
parking spaces," SoutheastCon, 2007.[6] Fabian, T. , "An Algorithm for Parking Lot Occupation
Detection,"
Computer Information Systems and Industrial Management Applications, 2008.
[7] Ichihashi, H.; Katada, T.; Fujiyoshi, M.; Notsu, A.; Honda, K.; , "Improvement in the performance of
camera
based vehicle detector for parking lot," Fuzzy Systems (FUZZ), 2010.
[8] Yusnita, R.; Fariza N. ; Norazwinawati B.; “Intelligent Parking Space Detection System Based on Image
Processing,” International Journal of Innovation, Management and Technology, Vol. 3, No. 3, June 2012.
[9] N. True;, “Vacant Parking Space Detection in Static Images,” Projects in Vision & Learning, University of
California,2007[Online].Available: http://www.cs.ucsd.edu/classes/wi07/cse190-a/reports /ntrue.pdf.
[10] Najmi Hafizi Bin Zabawi, Sunardi, Kamarul Hawari Ghazali, “Parking lot detection using image
processing method”, October 2013.
[11] Yusnita, R., Fariza Norbaya, and Norazwinawati Basharuddin. "Intelligent Parking Space Detection

16
 System Based onImage Processing." International Journal of Innovation, Management and Technology
3.3
(2012): 232.
[12] Banerjee, Sayanti, Pallavi Choudekar, and M. K. Muju. "Real time car parking system using image
processing." Electronics Computer Technology (ICECT), 2011 3rd International Conference on. Vol. 2.
EEE, 2011.

[13] Shaaban, Khaled, and Houweida Tounsi. "Parking Space Detection System Using Video Images."
Transportation Research Record: Journal of the Transportation Research Board 2537 (2015): 137-147.
[14] Singh, Himal Pratap, Om Prakash Uniyal, and Kireet Joshi. "An Approach to Implement Cost Efficient
Space Detection Technology with Lower Complexity for Smart Parking System." Indonesian Journal of
Electrical Engineering and Computer Science 15.3 (2015): 415-419.
[15] S. Saleh Al-Amri, N. V. Kalyankar, and Khamitkar S, “Image segmentation by using thershold
techniques,”
Journal of Computing. vol 2, Issue 5. MAY 2010, ISSN 2151-9617.
[16] Li, Shiqiang, Hussain Dawood, and Ping Guo. "Comparison of linear dimensionality reduction methods
in
image annotation." Advanced Computational Intelligence (ICACI), 2015 Seventh International
Conference on. IEEE, 2015.
[17] Mehmood, Rashid, Rongfang Bie, Hussain Dawood, and Haseeb Ahmad. "Fuzzy Clustering by Fast
Search
and Find of Density Peaks." In 2015 International Conference on Identification, Information, and
Knowledge in the Internet of Things (IIKI), pp. 258- 261. IEEE, 2015.

17