TRACKING THE OBJECTS IN IMAGES USING

MACHINE LEARNING

PROJECT REPORT

Submitted by

ARU MAAKADALAMUDHAN T 19TUIT003

GAYATHRI DEVI CJ 19TUIT019

KANISHKA R 19TUIT035

in partial fulfilment for the award of the degree

Of

BACHELOR OF TECHNOLOGY

IN

INFORMATION TECHNOLOGY

SRI KRISHNA COLLEGE OF TECHNOLOGY

An Autonomous Institution | Accredited by NAAC with ‘A’ Grade
Affiliated to Anna University
KOVAIPUDUR, COIMBATORE -641 042

MARCH 2024
CERTIFICATE
 BONAFIDE CERTIFICATE

This is to certify that this project report “Tracking Objects in Images using
Machine Learning” is the bonafide work of NITHISH KUMAR A P,
SANTHOSHKUMAR P, SARVEASWARAN M and SASI KUMAR G who
carried out the project work under my supervision.

SIGNATURE SIGNATURE
Dr A.Christy Jeba Malar Dr .S.Siamala Devi
SUPERVISOR HEAD OF THE DEPARTMENT
Associate Professor Associate Professor
Department of Information Technology Department of Information Technology
Sri Krishna College of Technology Sri Krishna College of Technology
Kovaipudur Kovaipudur
Coimbatore-42. Coimbatore-42.

Certified that the candidates were examined by us in the Project Work

viva-voce examination held on ............................... at Sri Krishna College of
Technology, Coimbatore -641 042.

INTERNAL EXAMINER EXTERNAL EXAMINER

ACKNOWLEDGEMENT
 ACKNOWLEDGEMENT

First and foremost we thank the Almighty for being our light and
for showering his gracious blessings throughout the course of this project.
We express our deep gratitude to our beloved Principal, Dr. M.G.
Sumithra, for providing all facilities.
We are grateful to our beloved Head, Computing Sciences
Dr.J.Shanthini, for her ever tireless and relentless support.
With the grateful heart, our sincere thanks to our Head of the
Department Dr. S Siamala Devi, Associate Professor, Department of
Information Technology for the motivation and all support to complete
the project work.
We thank our Project Coordinator Ms.T.Sangeetha, Assistant
Professor, Department of Information Technology, for her motivation and
support.
We extend our sincere thanks to our project supervisor Dr
A.Christy Jeba Malar, Associate Professor, Department of Information
Technology, for the valuable guidance and suggestions in all aspects that
aided us to ameliorate our skills.
We are thankful to all the Teaching and Non-Teaching Staff of
Department of Information Technology and to all those who have directly
and indirectly extended their help to us in completing this project work
successfully.
We extend our sincere thanks to our family members and our
beloved friends, who had been strongly supporting us in all our
endeavours.
 SRI KRISHNA COLLEGE OF TECH-
NOLOGY
(AN AUTONOMOUS INSTITUTION)
KOVAIPUDUR, COIMBATORE - 641042.

DEPARTMENT OF INFORMATION TECHNOLOGY

Vision of the Department

To be recognized as a Centre of Excellence for stimulating the creation

and exchange of knowledge by providing better service to enhance student
progress through effective teaching and learning process thereby leading to
innovation, professionalism, teaching work and continuous improvement.

Mission of the Department

1. To impart high quality technical and ethical knowledge to the stu-

dents.

2. To cultivate globally competent and collaborative IT graduates.

3. To nurture research and lifelong learning culture in the department.

 SRI KRISHNA COLLEGE OF TECH-
NOLOGY
(AN AUTONOMOUS INSTITUTION)
KOVAIPUDUR, COIMBATORE - 641042.

DEPARTMENT OF INFORMATION TECHNOLOGY

Program Educational Objectives (PEOs)

PEO1. Be able to apply the principles of computer science, information

systems, mathematics and related engineering field to solve real world
problems appropriate to the discipline and succeed in an information sys-
tem career.

PEO2. Be able to contribute and communicate effectively in multi-dis-

ciplinary teams to successfully complete projects and perform services re-
lated to information system to meet customer business objectives.

PEO3. Function ethically and responsibly, and will remain informed and
involved as full participants in our profession and our society.

PEO4. Engage in lifelong learning to remain current in their profession

and be leaders in our technological society.
 SRI KRISHNA COLLEGE OF TECH-
NOLOGY
(AN AUTONOMOUS INSTITUTION)
KOVAIPUDUR, COIMBATORE - 641042.

DEPARTMENT OF INFORMATION TECHNOLOGY

Program Outcomes

PO1 Engineering knowledge: Apply the knowledge of mathematics,

science, engineering fundamentals, and an engineering specialization
to the solution of complex engineering problems.
PO2 Problem analysis: Identify, formulate, research literature, and
analyze complex engineering problems reaching substantiated conclu-
sions using first principles of mathematics, natural sciences, and engi-
neering sciences.
PO3 Design/development of solutions: Design solutions for complex
engineering problems and design system components or processes that
meet the specified needs with appropriate consideration for the public
health and safety, and the cultural, societal, and environmental consid-
erations.
PO4 Conduct investigations of complex problems: Use research-
based knowledge and research methods including design of experi-
ments, analysis and interpretation of data, and synthesis of the infor-
mation to provide valid conclusions.
PO5 Modern tool usage: Create, select, and apply appropriate tech-
niques, resources, and modern engineering and IT tools including pre-
diction and modelling to complex engineering activities with an un-
derstanding of the limitations.
PO6 The engineer and society: Apply reasoning informed by the
contextual knowledge to assess societal, health, safety, legal and cul-
tural issues and the consequent responsibilities relevant to the profes-
sional engineering practice
PO7 Environment and sustainability: Understand the impact of the
professional engineering solutions in societal and environmental con-
texts, and demonstrate the knowledge of, and need for sustainable de-
velopment.
PO8 Ethics: Apply ethical principles and commit to professional
ethics and responsibilities and norms of the engineering practice.
PO9 Individual and team work: Function effectively as an individ-
ual, and as a member or leader in diverse teams, and in multidisci-
plinary settings.
PO10 Communication: Communicate effectively on complex engi-
neering activities with the engineering community and with society at
large, such as, being able to comprehend and write effective reports
and design documentation, make effective presentations, and give and
receive clear instructions.
PO11 Project management and finance: Demonstrate knowledge
and understanding of the engineering and management principles and
apply these to one’s own work, as a member and leader in a team, to
manage projects and in multidisciplinary environments.
PO12 Life-long learning: Recognize the need for, and have the
preparation and ability to engage in independent and life-long learning
in the broadest context of technological change.
 SRI KRISHNA COLLEGE OF TECH-
NOLOGY
(AN AUTONOMOUS INSTITUTION)
KOVAIPUDUR, COIMBATORE - 641042.

Program Specific Outcomes

PSO1:An ability to incorporate IT based solutions

into multi-disciplinary environment.
PSO2: An ability to identify user needs inclusive selection, creation,
evaluation and administrative of IT based infrastructure.
 SRI KRISHNA COLLEGE OF TECHNOLOGY
AN AUTONOMOUS INSTITUTION
Affiliated to Anna University and Approved by AICTE|
Accredited by NBA - AICTE and NAAC – UGC

KOVAIPUDUR, COIMBATORE - 641042.

DEPARTMENT OF INFORMATION TECHNOLOGY

PROJECT MAPPING WITH PROGRAM OUTCOMES AND PROGRAM SPECIFIC OUTCOMES

POs 1 2 3 4 5 6 7 8 9 10 11 12 PSO1 PSO2

<Your Project Ti-

3 3 3 3 3 3 3 3 3 3 3 3 3 3
tle>

Strong Associa- Moderate Associa- Weak Associa-

tion tion tion
3 2 1
TABLE OF CONTENTS
 TABLE OF CONTENTS

CHAPTER TITLE PAGE

NO. NO.
ABSTRACT x
LIST OF FIGURES xii
LIST OF ABBREVATIONS xiv
1. INTRODUCTION 1
1.1 Problem Statement 2

1.2 Overview of the project 2

2. LITERATURE REVIEW 3
2.1 Multiple Hypothesis Tracking 3

2.2 Background based detection and tracking 3

2.3 Segmentation based detection and tracking 4
2.4 Differential method based detection
4
2.5 Pixel level object detection and tracking 5

2.6 object detection and tracking 5

3. OBJECT DETECTION AND TRACKING THE 6

IMAGE USING DEEP LEARNING
6
3.1 Single Shot Detector
3.2 Mobile Nets Algorithm 7

4. SYSTEM DESIGN 9
5. IMPLEMENTATION 10
4.1 Object detection framing difference
10
4.2 Background subtraction 10
4.3 Object tracking
 6. SYSTEM DESIGN 11
6.1 Dataset collection 11
12
6.2 UML diagram
6.2.1 Use case diagram 12
13
6.2.2 Sequence diagram
6.3 Experimental/Simulation setup 13
6. RESULT AND ANALYSIS 14
7.1 Sample Code 14
22
7.2 Results &Discussion

7. CONCLUSION & FUTURE ENHANCEMENT 23

REFERENCES
ABSTRACT
 ABSTRACT

Real-time object detection and tracking is a vast, vibrant yet

inconclusive and complex area of computer vision. Due to its increased

utilization in surveillance, tracking system used in security and many

others applications have propelled researchers to continuously devise

more efficient and competitive algorithms. However, problems emerge in

implementing object detection and tracking in real-time; such as tracking

under dynamic environment, expensive computation to fit the real-time

performance, or multi-camera multi-objects tracking make this task

strenuously difficult. Though, many methods and techniques have been

developed, some famous and basic methods of object detection and

tracking is discussed in the literature review of this project. In the end, the

general applications and results of the proposed scheme are also given.
LIST OF FIGURES
 LIST OF FIGURES

FIGUR FIGURE TITLE PAGE

E NO. NO.
1. BASIC BLOCK DIAGRAM FOR OBJECT DETECTION
2. VGG-16 SSD MODEL
3. NORMAL CONVOLUTION
4. DEPTH WISE CONVOLUTION FILTERS
5. CONVOLUTION FILTER OF POINT WISE
CONVOLUTION IN DEPTH WISE CONVOLUTION
6. DETECTION OF HUMANS FROM BACKGROUND
7. TRACKING THE CAR
 CHAPTER 1

INTRODUCTION

Image processing is a method to perform some operations on an image, in

order to get an enhanced image or to extract some useful information from it. It is a
type of signal processing in which input is an image and output may be image or
characteristics/features associated with that image. Now a days, image processing
is among rapidly growing technologies. It forms core research area within
engineering and computer science disciplines too. There are two types of methods
used for image processing namely, analogue and digital image processing.
Analogue image processing can be used for the hard copies like printouts and
photographs. Image analysts use various fundamentals of interpretation while
using these visual techniques. Digital image processing techniques help in
manipulation of the digital images by using computers.

1.1 PROBLEM STATEMENT

A major challenge of existing object detection system which uses deep
learning library Tensorflow is non-optimal and low performance. Tensorflow is
very low-level and has unique structure, so it is hard to find an error and to debug.
So we reduce the computational time and increase the efficiency of the system by
replacing pytorch over other techniques. The system detects the objects and labels
the object in the input image using pytorch library of deep learning. Since the
system uses pytorch, the result will be more efficient and accurate, consumes
relatively less time than any other python library.

1.2 OVERVIEW OF THE PROJECT

Image Net on a large scale visual recognition challenge, for detection in-depth
learning, far exceeding the most traditional methods of artificial vision used in
literature. In artificial vision, the neural convolution networks are distinguished in
the classification of images. Fig. 1 shows the basic block diagram of detection and
tracking.

Fig. 1.1 Basic block diagram for object detection and tracking
Table 1.1 Comparison of Existing System with Proposed System

Author Year Key Contributions