FORM 2

THE PATENTS ACT 1970 (39 of 1970)

AND
The Patents Rules, 2003

PROVISIONAL / COMPLETE SPECIFICATION

(See section 10 and rule13)

TITLE OF THE INVENTION

OBJECT DETECTION PARKING SPOT COUNTER

APPLICANT

Country Of
Name Nationality Address
Residence
Student, Department of Computer
Science & Engineering Greater Noida
Naincy Yadav India India Institute of Technology Greater
Noida, Knowledge Park-II Greater
Noida, Uttar Pradesh -201310.
Student, Department of Computer
Science & Engineering Greater Noida
Neha Kumari India India Institute of Technology Greater
Noida, Knowledge Park-II Greater
Noida, Uttar Pradesh -201310.
Student, Department of Computer
Science & Engineering Greater Noida
Prashant Kumar Jha India India Institute of Technology Greater
Noida, Knowledge Park-II Greater
Noida, Uttar Pradesh -201310.
Student, Department of Computer
Science & Engineering Greater Noida
Ranjeet Kumar India India Institute of Technology Greater
Noida, Knowledge Park-II Greater
Noida, Uttar Pradesh -201310.
Student, Department of Computer
Rakesh Raushan India India
Science & Engineering Greater Noida

Signature Not Verified

Digitally Signed.
Name: AMRISH CHANDRA
Date: 15-Jul-2024 12:58:11
Reason: Patent Efiling
Location: DELHI
 Institute of Technology Greater
Noida, Knowledge Park-II Greater
Noida, Uttar Pradesh -201310.
Department of Computer Science &
Engineering Greater Noida Institute
Mr. Arjun Singh India India of Technology Greater Noida,
Knowledge Park-II Greater Noida,
Uttar Pradesh -201310.
Department of Computer Science &
Engineering Greater Noida Institute
Dr. Arun Kumar
India India of Technology Greater Noida,
Singh
Knowledge Park-II Greater Noida,
Uttar Pradesh -201310.
Department of Computer Science &
Engineering Greater Noida Institute
Dr. Sandeep Saxena India India of Technology Greater Noida,
Knowledge Park-II Greater Noida,
Uttar Pradesh -201310.

the following specification particularly describes the invention and the manner in which it is to
be performed.
 FIELD OF INVENTION

The present invention relates to the field of intelligent transportation systems (ITS)
and smart parking management solutions, more particularly, to a smart system for
object detection in parking spot counter.

5 BACKGROUND OF THE INVENTION

Efficient parking management is increasingly becoming a critical concern in urban

areas, commercial complexes, and public facilities. Traditional methods of parking
management often involve manual counting of vehicles or the use of basic sensor
technologies, which can be both labor-intensive and prone to errors. As the number
10 of vehicles on the road continues to grow, the demand for effective parking
solutions has escalated, necessitating the development of more advanced systems.

Conventional parking management systems typically rely on simple technologies

such as boom barriers, ticketing systems, and basic sensors like inductive loops,
pressure sensors, or ultrasonic detectors. These systems, while functional, present
15 several drawbacks that hinder their efficiency and accuracy. Manual counting
requires human intervention, which is not only time-consuming but also increases
labour costs. Human error can lead to inaccurate counting and reporting of available
parking spaces. Manual processes cannot provide real-time updates, leading to
potential delays and confusion for drivers searching for parking. These sensors
20 require installation under the pavement, which can be costly and disruptive to
existing infrastructure. Physical sensors are susceptible to wear and tear, requiring
regular maintenance and replacements. Environmental factors such as debris, water,
and temperature variations can affect sensor accuracy, leading to false readings.
Ultrasonic sensors may have limited range and can be affected by environmental
25 noise, leading to inaccuracies in vehicle detection. The effectiveness of ultrasonic
sensors is highly dependent on their precise positioning and alignment.
Conventional systems often fail to provide real-time information, resulting in
outdated and inaccurate data on parking availability. Without real-time data,
parking management cannot optimize the utilization of available spaces, leading to

2
 inefficiencies. Expanding traditional parking systems to accommodate larger
parking areas involves significant costs in terms of additional sensors, infrastructure
modifications, and labor. Integrating conventional systems with modern
technologies and platforms can be complex and costly. Drivers often face
5 difficulties in finding available parking spots, leading to frustration and wasted
time. Traditional systems lack advanced features such as real-time notifications,
reservation capabilities, and historical data analysis, which can enhance user
experience and operational efficiency.

Therefore, there remains a need in the art for a smart system for object
10 detection in parking spot counter that does not suffer from the above-mentioned
deficiencies or at least provides a viable, economical and effective solution.

OBJECTS OF THE INVENTION

Some of the objects of the present disclosure, which at least one embodiment herein
satisfies, are as follows.

15 It is an object of the present disclosure to ameliorate one or more problems of the

prior art or to at least provide a useful alternative.

An object of the present disclosure is to provide a smart system for object

detection in parking spot counter.

An object of the present disclosure is to provide a smart system for object

20 detection in parking spot counter that can accurately detects the presence of vehicles
in parking spots using high-resolution cameras and a combination of ultrasonic,
infrared, and magnetic sensors.

An object of the present disclosure is to provide a smart system for object

detection in parking spot counter that can employ advanced machine learning
25 algorithms to enhance detection accuracy and minimize false positives and
negatives.

An object of the present disclosure is to provide a smart system for object

detection in parking spot counter that can offers real-time updates on parking spot

3
 availability, reducing the time drivers spend searching for available parking.

An object of the present disclosure is to provide a smart system for object

detection in parking spot counter that can implement efficient communication
protocols to ensure timely data transfer between sensors, processing units, and user
5 interfaces.

An object of the present disclosure is to provide a smart system for object

detection in parking spot counter that can create a user-friendly interface, accessible
via mobile apps or web dashboards, to display real-time parking spot status,
notifications, and historical data.

10 An object of the present disclosure is to provide a smart system for object

detection in parking spot counter that can

An object of the present disclosure is to provide a smart system for object

detection in parking spot counter that can enable parking operators to monitor and
manage parking spaces more efficiently, utilizing real-time data and historical
15 trends.

An object of the present disclosure is to provide a smart system for object

detection in parking spot counter that can provide tools for analyzing parking usage
patterns to inform decision-making and improve operational efficiency.

An object of the present disclosure is to provide a smart system for object

20 detection in parking spot counter that can ensure compatibility with various parking
environments and the ability to integrate with existing infrastructure.

An object of the present disclosure is to provide a smart system for object

detection in parking spot counter that can implement security measures to protect
data and communication channels from unauthorized access and breaches.

25 An object of the present disclosure is to provide a smart system for object

detection in parking spot counter that can reduce the environmental impact of
parking management by minimizing the time vehicles spend idling while searching
for parking spots.

4
 SUMMARY OF THE INVENTION

The following presents a simplified summary of the invention in order to provide a

basic understanding of some aspects of the invention. This summary is not an
extensive overview of the present invention. It is not intended to identify the
5 key/critical elements of the invention or to delineate the scope of the invention. Its
sole purpose is to present some concept of the invention in a simplified form as a
prelude to a more detailed description of the invention presented later.

An embodiment of the present invention is to provide a smart system for

object detection in parking spot counter. The Object Detection Parking Spot
10 Counter is a smart parking management system that uses a combination of high-
resolution cameras, ultrasonic, infrared, and magnetic sensors, along with advanced
machine learning algorithms, to detect and count vehicles in parking spots
accurately. This system provides real-time updates on parking spot availability,
enabling drivers to quickly find and reserve parking spaces through a user-friendly
15 mobile app or web dashboard. The invention aims to improve parking efficiency,
reduce congestion, and enhance the overall user experience by offering features
such as real-time monitoring, reservation capabilities, and usage-based payment
systems. Additionally, it benefits parking lot operators by optimizing parking space
management and providing valuable insights into usage patterns. The system is
20 designed to be scalable, cost-effective, and easy to integrate with existing
infrastructure.

BRIEF DESCRIPTION OF THE DRAWINGS

So that the manner in which the above recited features of the present invention can
be understood in detail, a more particular description of the invention, briefly
25 summarized above, may have been referred to by embodiments, some of which are
illustrated in the appended drawings. It is to be noted, however, that the appended
drawings illustrate only typical embodiments of this invention and are therefore not
to be considered limiting of its scope, for the invention may admit to other equally
effective embodiments.

5
 These and other features, benefits, and advantages of the present invention will
become apparent by reference to the following text figure, with like reference
numbers referring to like structures across the views, wherein

Fig 1: illustrate a smart system for object detection in parking spot counter., in
5 accordance with an embodiment of the present invention.

DETAILED DESCRIPTION OF THE INVENTION

The following description is of exemplary embodiments only and is not

intended to limit the scope, applicability or configuration of the invention in any
way. Rather, the following description provides a convenient illustration for
10 implementing exemplary embodiments of the invention. Various changes to the
described embodiments may be made in the function and arrangement of the
elements described without departing from the scope of the invention.

While the present invention is described herein by way of example using

embodiments and illustrative drawings, those skilled in the art will recognize that
15 the invention is not limited to the embodiments of drawing or drawings described,
and are not intended to represent the scale of the various components. Further, some
components that may form a part of the invention may not be illustrated in certain
figures, for ease of illustration, and such omissions do not limit the embodiments
outlined in any way. It should be understood that the drawings and detailed
20 description thereto are not intended to limit the invention to the particular form
disclosed, but on the contrary, the invention is to cover all modifications,
equivalents, and alternatives falling within the scope of the present invention as
defined by the appended claim. As used throughout this description, the word
"may" is used in a permissive sense (i.e. meaning having the potential to), rather
25 than the mandatory sense, (i.e. meaning must). Further, the words "a" or "an" mean
"at least one” and the word “plurality” means “one or more” unless otherwise
mentioned. Furthermore, the terminology and phraseology used herein is solely
used for descriptive purposes and should not be construed as limiting in scope.
Language such as "including," "comprising," "having," "containing," or

6
 "involving," and variations thereof, is intended to be broad and encompass the
subject matter listed thereafter, equivalents, and additional subject matter not
recited, and is not intended to exclude other additives, components, integers or
steps. Likewise, the term "comprising" is considered synonymous with the terms
5 "including" or "containing" for applicable legal purposes.

Figure 1: illustrate a smart system for object detection in parking spot counter, in
accordance with an embodiment of the present invention. The smart system for
object detection in parking spot counter comprises a plurality of high-resolution
cameras, a plurality of sensor, a processing unit, a communication module, a user
10 interface. The plurality of high-resolution cameras is positioned. The plurality of
high-resolution cameras is configured to capture images or videos of a parking area.
The plurality of sensor includes ultrasonic, infrared, and magnetic sensors
configured to detect the presence of vehicles in parking spots. The processing unit
is configured to run object detection algorithms and analyses data from the plurality
15 of high-resolution cameras and plurality of sensor. The communication module is
configured to transmit real-time parking spot availability data to a central server.
The user interface accessible is configured to display real-time parking spot status
and enable reservations.

In accordance with an embodiment of the present invention, the processing

20 unit employs machine learning algorithms, including Mask R-CNN, to accurately
detect vehicles and determine their occupancy status in parking spots.

In accordance with an embodiment of the present invention, the feature for

users to reserve parking spots in advance through the user interface, wherein the
system verifies and confirms the availability of the selected spot.

25 In accordance with an embodiment of the present invention, the communication

module utilizes wireless communication technologies, including Wi-Fi, Bluetooth,
and LoRa, to ensure timely data transfer between sensors, processing units, and user
interfaces.
In accordance with an embodiment of the present invention, the

7
 administrator interface for parking lot operators to monitor and manage parking
spaces, analyze usage patterns, and adjust pricing dynamically.

In accordance with an embodiment of the present invention, the user

interface provides real-time notifications about parking spot availability,
5 reservation confirmations, and payment status.

In accordance with an embodiment of the present invention, the processing

unit includes edge devices for real-time data processing to reduce latency and
improve detection accuracy.

In accordance with an embodiment of the present invention, the initial setup

10 involves manually marking parking lot boundaries and designated parking regions
using a frame from the camera or stream and the Polygon Selector feature in the
Matplotlib module.

In accordance with an embodiment of the present invention. the system

provides real-time monitoring and alerts for potential security issues, such as theft
15 or unauthorized access to the parking area.

In accordance with an embodiment of the present invention, the system

supports cashless payment options for parking, integrated within the user interface,
facilitating seamless transactions for users.

In accordance with an embodiment of the present invention, the system

20 includes

a. Sensors:

Cameras: High-resolution cameras are installed at strategic locations to capture

images or videos of the parking area.

Ultrasonic Sensors: These sensors detect the presence of vehicles in parking spots
25 by measuring distance.

Infrared Sensors: Used to detect vehicles by sensing the heat they emit.

8
 Magnetic Sensors: Detect vehicles through disruptions in the magnetic field caused
by metallic objects.

b. Processing Unit:

Microcontroller/Microprocessor: Handles data processing and runs detection

5 algorithms.

Edge Devices: Perform real-time processing to reduce latency.

c. Communication Module:

Wi-Fi/Bluetooth: Enables wireless communication with a central server.

LoRa: Provides long-range, low-power communication capabilities.

10 d. Software:

Object Detection Algorithm: Machine learning models such as Mask R-CNN

(Mask Region-based Convolutional Neural Networks) are used for detecting
vehicles.

Data Processing: Filters and analyzes data from sensors.

15 User Interface: Displays parking spot status in real-time through a mobile app or
web dashboard.

In accordance with an embodiment of the present invention, the system the

input video, the Mask R-CNN object detection model is utilized to identify cars and
their bounding boxes. Once these bounding boxes are obtained, the Intersection
20 over Union (IoU) for each pair of bounding boxes and parking spot coordinates is
computed. If the IoU value for any parking spot exceeds a specified threshold, that
parking spot is classified as occupied.

a. Detection of Parking Spots:

The initial stage of the parking space detection system involves identifying the
25 parking slots. Several methods can accomplish this, including detecting parking
lines using edge detectors offered by OpenCV. However, this strategy's reliability
diminishes in parking areas without predetermined boundaries. An alternative

9
 approach assumes that vehicles remaining immobile for an extended duration are
parked. Valid parking spaces, in this context, refer to designated zones where
stationary vehicles are located. This approach is also prone to false positives and
negatives. When automation demonstrates its lack of reliability, manual
5 intervention may be necessary. Our technique differs from space-based methods as
it does not require labeling and training for each individual parking facility. Instead,
it requires the initial marking of parking lot boundaries and surrounding road areas
during setup. Our method involves selecting a frame from the camera or stream of
the parking area and manually indicating the parking regions. The Matplotlib
10 module in Python, with its Polygon Selector feature, enables precise selection of
polygonal regions.

b. Parking Booking and Management Model:

The system allows users to input their credentials, choose a location, and select a
date and time for their reservation. The system verifies the availability and allows
15 users to review and confirm their booking. An administrator can then review and
either accept or reject the reservation, informing the user of the status and
completing the transaction if accepted.

3. Benefits for Society:

Drivers:

20 Reduced Time Spent Searching: Parking spot management systems eliminate the
need to circle around for an open spot, saving drivers considerable time.

Less Stress Levels: Knowing a spot is reserved in advance reduces anxiety, making
driving more enjoyable and stress-free.

Enhanced Efficiency: Drivers can plan their trips more efficiently by reserving a
25 parking space in advance, which is especially helpful for time-sensitive
appointments or errands.

Better Accessibility: Parking management systems can integrate accessibility

features, making it easier for drivers with impairments to find and book accessible
parking spaces.

10
 Potential Cost Savings: Demand-driven dynamic pricing can offer more affordable
parking options during off-peak hours.

Lower Fuel Consumption: Quickly locating parking reduces fuel use, saving money
and lowering environmental impact.

5 Convenience: Reserving a place in advance ensures a parking spot upon arrival,

especially helpful in crowded locations or during rush hour.

Better Navigation: Some systems integrate with navigation apps, guiding drivers
directly to open spots.

Cashless Payments: Users can pay for parking without cash or tickets using the app.

10 Parking Lot Operators:

Increased Revenue: Streamlined payment procedures and demand-driven variable

pricing can boost revenue.

Enhanced Efficiency: Real-time data on parking availability allows for better

management of parking facilities.

15 Reduced Traffic Congestion: Better traffic flow around parking lots reduces
congestion on surrounding roads.

Enhanced Information Gathering: Parking management systems provide valuable

insights into usage trends, aiding future planning and development.

Environmental:

20 Lowered Environmental Impact: Reducing the time cars spend searching for
parking decreases idle emissions, contributing to a cleaner environment.

Minimizing Vehicle Emissions: Efficient parking management reduces overall

emissions of pollutants like hydrocarbons, nitrogen oxides, and carbon monoxide.

Better Air Quality: Fewer cars idling and searching for parking improves air quality,
25 benefiting everyone's respiratory health.

Better Use of Land: Effective management systems can reduce the need for large
parking lots, freeing up space for parks, green areas, or housing developments,

11
 creating a more balanced and sustainable urban environment.

While considerable emphasis has been placed herein on the specific features
of the preferred embodiment, it will be appreciated that many additional features
can be added and that many changes can be made in the preferred embodiment
5 without departing from the principles of the disclosure. These and other changes in
the preferred embodiment of the disclosure will be apparent to those skilled in the
art from the disclosure herein, whereby it is to be distinctly understood that the
foregoing descriptive matter is to be interpreted merely as illustrative of the
disclosure and not as a limitation.

12
We Claim,

1. A smart system for object detection in parking spot counter comprising:

a plurality of high-resolution cameras positioned configured to
capture images or videos of a parking area;
a plurality of sensor includes ultrasonic, infrared, and magnetic
sensors configured to detect the presence of vehicles in parking spots;
a processing unit configured to run object detection algorithms and
analyse data from the plurality of high-resolution cameras and plurality of
sensor;
a communication module configured to transmit real-time parking
spot availability data to a central server;
a user interface accessible configured to display real-time parking
spot status and enable reservations.
2. The system as claimed in claim 1, wherein the processing unit employs
machine learning algorithms, including Mask R-CNN, to accurately detect
vehicles and determine their occupancy status in parking spots.
3. The system as claimed in claim 1, wherein the feature for users to reserve
parking spots in advance through the user interface, wherein the system
verifies and confirms the availability of the selected spot.
4. The system as claimed in claim 1, wherein the communication module
utilizes wireless communication technologies, including Wi-Fi, Bluetooth,
and LoRa, to ensure timely data transfer between sensors, processing units,
and user interfaces.
5. The system as claimed in claim 1, wherein the administrator interface for
parking lot operators to monitor and manage parking spaces, analyze usage
patterns, and adjust pricing dynamically.
6. The system as claimed in claim 1, wherein the user interface provides real-
time notifications about parking spot availability, reservation confirmations,
and payment status.

13
 7. The system as claimed in claim 1, wherein the processing unit includes edge
devices for real-time data processing to reduce latency and improve
detection accuracy.
8. The system as claimed in claim 1, wherein the initial setup involves
manually marking parking lot boundaries and designated parking regions
using a frame from the camera or stream and the Polygon Selector feature
in the Matplotlib module.
9. The system as claimed in claim 1, wherein the system provides real-time
monitoring and alerts for potential security issues, such as theft or
unauthorized access to the parking area.
10. The system as claimed in claim 1, wherein the system supports cashless
payment options for parking, integrated within the user interface,
facilitating seamless transactions for users.

Dated this 15 July 2024

Dr. Amrish Chandra

Agent of the Applicant
IN/PA-2959

14
TITLE: OBJECT DETECTION IN PARKING SPOT COUNTER

ABSTRACT

The present invention relates to a object detection in parking spot counter. The
system is integrated with high-resolution cameras, ultrasonic, infrared, and
magnetic sensors, and advanced machine learning algorithms. The smart system
accurately detects and monitors parking spot occupancy in real-time, ensuring
efficient utilization of parking spaces. The drivers benefit from a user-friendly
interface, accessible via mobile app or web dashboard, providing instant updates on
available spots and enabling seamless reservations and payments. Real-time data
processing by the central unit and precise object detection algorithms, including
mask r-CNN, ensure high accuracy in identifying vehicle presence. The system
supports dynamic pricing and enhances operational efficiency for parking lot
operators by optimizing space usage and improving traffic flow. Designed for
scalability and integration with existing infrastructure, the object detection parking
spot counter addresses urban congestion challenges while enhancing user
convenience and urban mobility management.

15