B. V. V.

Sangha’s

BASAVESHWAR ENGINEERING COLLEGE (AUTONOMOUS),

BAGALKOT-587 102

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

For the academic year

2019-2020

Project Phase-I Report

on

“Image Processing Techniques for Surveillance using Drones”

Under the Guidance of

Dr. V. B. Pagi
Professor

Submitted by:

Name USN

Deepak Kulkarni 2BA16CS008

D Teja 2BA16CS010

Karthik V Sankanagoudar 2BA16CS019

1
 B. V. V. Sangha’s
BASAVESHWAR ENGINEERING COLLEGE (AUTONOMOUS),

BAGALKOT-587 102

Department of Computer Science & Engineering

For the academic year

2019-2020

CERTIFICATE

This is to certify that Mr. Deepak Kulkarni(2BA16CS008), Mr. D

Teja(2BA16CS010), Mr. Karthik V. Sankanagoudar(2BA16CS019) has
satisfactorily completed the project phase-I on “Image Processing Techniques
For Surveillance using Drones”, for the fulfillment of their courses in
Computer Science in engineering as prescribed by Basaveshwar Engineering
College(Autonomous), Bagalkot during the academic year 2019-2020.

PLACE: Bagalkot

DATE: 22-11-2019

Under the Guidance of Project Coordinator Head of the Department

Dr. V. B. Pagi Dr. S. M. Hatture Dr. S. V. SABOJI

Name of Examiners Signature of Examiner

1…………………… 1………………………
2………………….... 2…………………........
3………………….... 3………………….........

2
 ACKNOWLEDGMENT

I have taken efforts in this project. However, it would not have been possible
without the kind support and help of many individuals and organizations. I
would like to extend my sincere thanks to all of them.

I am highly indebted to Dr. V. B. Pagi for his guidance and constant

supervision as well as for providing necessary information regarding the project
& also for his support in completing this report. I would like to express my
gratitude towards Dr. S. M. Hatture for his kind co-operation and
encouragement which helped me in completion of this project. We thank our
beloved Principal Dr. C. B. Shivayogimath for his constant help and support
throughout. Our special thanks to our Head of the department Dr. S. V. Saboji
who supported us in making this project a successful one.

We would like to thank all the teaching and non-teaching staff of department of
Computer Science and Engineering for their coordination and support.

3
 ABSTRACT

In today's world, there is a growing need for surveillance in order to

maintain the decorum at a place and ensure the safety and security of the people.
An aerial surveillance system will be worthwhile in this regard. The Deep-
learning based computer vision is now powering these drones for aerial
surveillance.

This project is a combination of both software and hardware

aspects. The project is mainly based on the safety and security-focused
application in various areas that we identified as main targets which will help
the security forces. The security threats have been increasing gradually, there is
a need for identifying and delivering the information regarding these threats to
the security forces quickly. So, they can take action early, we are using the
drones which make surveillance in the particular geographical area and live
streaming of the images to the control room where the captured images are
interpreted, analyzed, processed and give an alert message to the security forces
automatically. The security forces check the abnormality detected and can take
necessary actions immediately, even the images captured by drones, act as the
proof to identify the person/situation responsible for the hazards.

4
 TABLE OF CONTENTS

Chapter Chapter Headings Page No.

No.

1. INTRODUCTION
6

2. LITERATURE SURVEY 9

3. ISSUES AND CHALLENGES 18

4. MOTIVATION,SCOPE AND PROBLEM DEFINITION 19

5. FLOW CHART OF PROPOSED SOLUTION 21

6. CONCLUSION 26

REFERENCES 27

5
 1. INTRODUCTION

In the past decade there has been a great technological development

like machine learning,IOT,quantum computing.But not only these technological
development even the problems in the “era of technology” like security
threats,terror attacks,natural disasters have also been increasing.Drones provide
the useful missions to prevent hazards,accidents and identify the abnormality.So
we are catching up these above mentioned technologies to solve the problems
regarding the security at some level.While they originated mostly in military
applications, their use is rapidly expanding to commercial, scientific,
recreational, agricultural, and other applications, product deliveries(like amazon
prime air), aerial photography, smuggling, and drone racing.Civilian
UAV’s(unmanned aerial vehicle) now vastly outnumber military UAV’s, with
estimates of over a million sold by 2018 which they use for hobby purpose
based on their interests.

They can be used in serious/commercial applications,they are timely,

cost-effective and very rich data acquisition, high-resolution images by them
made use of drones popular.These intelligent autonomous systems and
autonomous/semi-autonomously operating swarms also performs the different
tasks provide to useful missions like detecting the abnormalities,hazards in the
particular environment and report it to the operator, especially in the border &
costal surveillance.

In this report we provide a brief overview of safety and security-focused

application areas that we identified as main targets which will help the security
forces.After that we mention how we have incorporate those technologies into a
drone and have made them work together harmoniously in order to achieve our
desired aerial surveillance system. We also discussed a number of challenges
related to the deployment of drones in general and to their deployment within
the identified application areas in particular.

6
 The Drone built on pixhawk module

The aim is to provide fast and efficient surveillance at an affordable

rate so that it can be used widely at private, institutional and governmental level.

Various fields various drones are used:

Due to the great versatility and its large applications, the industry
experts are focusing on the unimaginable applications that has been never done
before.Even the development and research is also going on by communities like
pixhwak, dronecode.org, weforum.

1) The using of these drones in agriculture for the detection of weeds, or

unusual growth of crop in some slots of large field, detection of ripened
fruits for the large trees

2) Even they are used in the large construction sites(like dams) to determine
and keep monitoring the progress of work and labour.

3) Effective flood survey can be done by using drones, which will help to
provide the necessary flood relief actions.

7
Requirements and implementation details:

As this project is a combination of both hardware and software

aspects.we need the hardware entities to implement this we use the pixhawk
module which is an independent open-hardware project that aims to provide the
standard for readily-available, hiqh-quality and low-cost autopilot hardware
designs for the academic, hobby and developer communities.

We will be using the OpenCV the python library for programming

functions mainly aimed at real-time computer vision for image detection and
tensor flow which is also a python library used for machine learning
applications such as neural networks to build the deep-neural network models to
extract,process and analysis for getting the data from the images,The software
used anaconda which is a scientific Python distribution for developing the
image detection and classifying models.

The images captured from the drone is sent to the control room system
using the RTMP(real time messaging protocol) which is a part of TCP protocol.

The project also includes the control room where the captured images of
drones are processed by the built neural network models and alerts the security
crew if any abnormality is detected later ,the crew can verify these images
immediately and take quick actions required.

There is increasing reference made to the potential of using UAVs as

autonomous or semi-autonomous which have been used in the various fields in
the next literature section.

8
2-LITERATURE SURVEY

1. SAURAV KUMAR and E.KANNIGA,"Literature Survey On Unmanned

Aerial Vehicle",2018
The research work on this paper aims to develop an unmanned aerial vehicle
equipped with modern technologies various civil military applications. It is an
automatic system The shrinking size and increasing capabilities of microelectr-
onic devices in recent years has opened up the doors to more capable autopilot
and pushed for more real time UAVs applications. The Unmanned Aerial
Vehicle (UAV) market is to grow dramatically by 2020, as military, civil and
comercial applications continue to develop. Potential changes in air traffic
management include the creation of an information It defines a UAV to be ”An
aircraft which is management system to exchange information among Air
Traffic Management users and providers, the introduction of navigation, and the
development of alternative separation procedures.

2. Kalpesh R. Dashpute and Nilesh S. bawa "UAV-Based Traffic Analysis: A

Universal Guiding Framework", 2017
The Unmanned Aerial Vehicles (UAVs) commonly also known as drones are
considered as one of the most dynamic and multi-dimensional emerging
technologies of the modern era. Recently, this technology has found multiple
applications in the transportation field as well; ranging from the traffic
surveillance applications to the traffic network analysis for the overall
improvement of the traffic flow and safety conditions. However, in order to
conduct a UAV-based traffic study, an extremely diligent planning and
execution is required followed by an optimal data analysis and interpretation
procedure. This paper presents a universal guiding framework for ensuring a
safe and efficient execution of a UAV-based study.

3. Hanno Hildmann and Ernö Kovacs ,"Using Unmanned Aerial Vehicles

(UAVs) as Mobile Sensing Platforms (MSPs) for Disaster Response, Civil
Security and Public Safety",2019
The use of UAVs in areas ranging from agriculture over urban services to
entertainment or simply as a hobby has rapidly grown over the last years.
Regarding serious/commercial applications, UAVs have been considered in the
literature, especially as mobile sensing/actuation platforms (i.e., as a delivery
platform for an increasingly wide range of sensors and actuators). With regard

9
to timely, cost-effective and very rich data acquisition, both, NEC Research as
well as TNO are pursuing investigations into the use of UAVs and swarms of
UAVs for scenarios where high-resolution requirements, prohibiting
environments or tight time constraints render traditional approaches ineffective.

4.Nanchen Nimyel and et al.,"Security Of Unmanned Aerial Vehicles: A

Literature Review And Research Directions",2018
Unmanned Aerial Systems (UAS)- air vehicles equipped with sensors and
software that enable the craft to fly without a human pilot on board. This is an
emerging technology with a tremendous potential to revolutionize warfare and
to enable new civilian applications. Vulnerabilities of UAS being hacked exist,
and each of these attacks requires a different set of skills and targets a different
set of vulnerabilities. There are claims of the existence of “unhackable” UAS
based on the use of formal methods in the kernel of its operating system.

5.Hazim Shakhatreh and et al.,”Unmanned Aerial Vehicles: A Survey on

Civil Applications and Key Research Challenges",2018
The use of unmanned aerial vehicles (UAVs) is growing rapidly across many
civil application domains including realtime monitoring, providing wireless
coverage, remote sensing, search and rescue, delivery of goods, security and
surveillance, precision agriculture, and civil infrastructure inspection. Smart
UAVs are the next big revolution in UAV technology promising to provide new
opportunities in different applications, especially in civil infrastructure in terms
of reduced risks and lower cost. Civil infrastructure is expected to dominate the
more that $45 Billion market value of UAV usage.

6. Gilles Albeaino,”A systematic review of Unmanned Aerial Vehicle

application areas and technologies in the AEC domain",2019
The recent increase in the integration of unmanned aerial vehicles (UAVs) in
civilian usage stems mainly from modern technological advancements and the
devices’ abilities to accomplish civilian tasks in a quick, safe, and cost-efficient
manner. One sector that witnessed tremendous UAV impact is the Architecture,
Engineering, and Construction (AEC) industry. Among several AEC
applications, UAV technology is currently being implemented for building and
bridge inspection, progress monitoring, and urban planning. The following
review aims at thoroughly classifying all AEC-related UAV applications within
the past decade, extending the understanding of the current state of UAV

10
implementation in the AEC domain, and outlining relevant research trends in
this setting.

7. Ciara Bracken-Roche and et al.,"Surveillance Drones: Privacy Implications

of the Spread of Unmanned Aerial Vehicles ",2014
Surveillance drones are a fresh development that, like all other surveillance, is
deeply ambiguous. The social benefits are clearly articulated by their promoters,
but potential new challenges to privacy, civil liberties, and human rights receive
comparatively little attention. While acknowledging the considerable scope for
positive civilian exploitation of the capacities of Unmanned Aerial Vehicles
(UAVs), this report focuses primarily on the need to consider the social, legal,
and ethical challenges from the outset. We discuss aerial vehicles, sometimes
automated but normally piloted from the ground, that carry cameras and, on
occasion, sensing devices.

8. "Literature Review on UAV"

Decision support systems integrate a multitude of available technologies that
collect, analyze, display, and disseminate data to a broad range of user
communities. Dependent upon specific goals, acquired data becomes useful
information, readily available to decision-making managers, when appropriately
communicated. For environmental reconnaissance and assessment operations,
remote sensing and geographical information systems are integral geospatial
components for interpreting real-world occurrences of atmospheric and land-
based phenomenon. The Unmanned Aerial Vehicle (UAV) is one of a suite of
tools that has recently been used independently and as an integrated remote
sensing resource.

9.Anuj Puri ,"A Survey of Unmanned Aerial Vehicles (UAV) for Traffic
Surveillance ",2018
The United States Department of Transportation (DOT) has been interested for
the past several years in obtaining data on traffic trends and to monitor and
control traffic in realtime. Currently, there are several methods by which the
DOT regulates and monitors road transport. Cameras mounted on towers,
detectors embedded in pavements or pneumatic tubes, and unmanned aircraft
have been proven to be expensive and time-consuming solution candidates.
However, aerial monitoring has the potential to yield detailed information to
help traffic planners, as well as commuters. Unmanned Aerial Vehicles (UAVs)
may provide a “bird’s eye view” for traffic surveillance, road conditions and

11
emergency response. The purpose of this technical report is to provide a survey
of research related to the application of UAVs for traffic management.

10. Abdou Fall,"Assistive Drone Technology: Using Drones to Enhance

Building Access ",2018
This thesis explores improvements to assistive capability so that those living
with a physical disability can also maneuver their environment, especially
buildings, with ease. To do so, this study outlines a step-by-step process to
understand better how buildings can be mapped using drone technologies as a
method for members of society with physical challenges, especially mobility, to
determine ease of accessibility before entering a building. By way of interview,
observation, and survey, this thesis embarks upon requirement analysis for the
use of drones as assistive technology.

11. Truls Hallberg Tønnessen ,"Islamic State and Technology – A Literature

Review",2017
This article offers an overview of the literature on how the Islamic State has
used different technologies, primarily within the fields of drone technology,
CBRN and communication technology. The author argues that the primary
strength of the Islamic State, and terrorist groups in general, is not in the
acquisition and use of advanced technology, but the innovative and improvised
use of less advanced, but easily accessible, technology. A gap identified in the
existing research is the question of priority – why and under what circumstances
would a terrorist group allocate some of its (usually) limited resources in order
to develop or acquire new technological capabilities?

12.Rachel M. Burns,"Unmanned Aerial Vehicles",2018

An unmanned aerial vehicle (UAV) is an aircraft that carries no human pilot or

passengers. UAVs — sometimes called “drones” — can be fully or partially
autonomous but are more often controlled remotely by a human pilot. RAND
research has contributed to the public discussion on the use of drones for
warfare and surveillance.

12
13.Isha Kalra and et al.,"DroneSURF: Benchmark Dataset for Drone-based
Face Recognition",2019
Unmanned Aerial Vehicles (UAVs) or drones are often used to reach remote
areas or regions which are inaccessible to humans. Equipped with a large field
of view, compact size, and remote control abilities, drones are deemed suitable
for monitoring crowded or disaster-hit areas, and performing aerial surveillance.
While research has focused on area monitoring, object detection and tracking,
limited attention has been given to person identification, especially face
recognition, using drones. This research presents a novel large-scale drone
dataset, DroneSURF: Drone Surveillance of Faces, in order to facilitate research
for face recognition. The dataset contains 200 videos of 58 subjects, captured
across 411K frames, having over 786K face annotations.

14.Vroegindeweij," Autonomous unmanned aerial vehicles for agricultural

applications",2014
Drones or Unmanned Aerial Vehicles (UAVs) receive a growing interest in
media and literature, not only for military and surveillance applications, but also
as toys and for agricultural purposes. In this research, we reviewed the current
state of art of UAV technology. Moreover, we define potential agricultural
application cases where autonomous UAVs can be used, which in the end is
translated to a research agenda to enable this innovation. Main-stream
development started in US army, based on the plane principle, while later
adding helicopter-based motion to increase versatility. First applications
consisted of observation tasks and bombing targets, and extended to spraying of
fluids with plane-like UAVs. These are still the main purposes (both civil and in
military) of UAVs.

15.Dr.Markus Kückelhaus,"UNMANNED AERIAL VEHICLE IN

LOGISTICS",2014
Recent worldwide media attention has put unmanned aerial vehicles (UAVs) in
the spotlight. Their many different applications make for great headlines – they
are being used for military purposes in Pakistan (US Army), for development
aid work in Africa (Matternet), and for parcel delivery in Germany (DHL Paket).
Some organizations are using UAVs specifically because of this high level of
interest. Good examples are the world’s largest online retailer, Amazon and the
world´s largest logistics company DPDHL, which are testing UAV delivery.
And countless start-ups have jumped on the bandwagon to gain publicity and
boost sales (e.g., Zookal’s stated intention to deliver textbooks via UAVs in
Australia).

13
16.Eren Unlu and et al.," Deep learning-based strategies for the detection
and tracking of drones using several cameras",2019
Commercial Unmanned aerial vehicle (UAV) industry, which is publicly
known as drone, has seen a tremendous increase in last few years, making
these devices highly accessible to public. This phenomenon has immediately
raised security concerns due to fact that these devices can intentionally or
unintentionally cause serious hazards. In order to protect critical locations, the
academia and industry have proposed several solutions in recent years.
Computer vision is extensively used to detect drones autonomously compared
to other proposed solutions such as RADAR, acoustics and RF signal analysis
thanks to its robustness.

17.Rachel Rhodes and Natalie Spiegel ,"Of The Effects Of Unmanned

Aircraft Systems On Seabirds And Marine Mammals",2017
Unmanned Aircraft Systems (UAS) have become increasingly prevalent in the
last decade. The combined total hobbyist and commercial UAS sales are
expected to rise from 2.5 million in 2016 to 7 million in 2020 (FAA, 2017).
However, despite this rapid growth in UAS deployment, knowledge of the
effects of UAS on wildlife is very limited to date. Additionally, there have been
a limited number of studies examining the effects of UAS operations on either
seabirds or marine mammals, particularly when flown at lower altitudes.

18.Dennis Vincenzi," Public Perception of Unmanned Aerial Systems (UAS):

A Survey of Public Knowledge Regarding Roles, Capabilities, and Safety
While Operating Within the National Airspace System (NAS) ",2013
A variety of challenges to the successful assimilation of Unmanned Aircraft
Systems (UASs) into the National Airspace System (NAS) exists, Aside from
technical and legislative challenges, another setback has recently surfaced when
the FAA suspended its selection process for UAS test sites due to privacy
concerns. This new obstacle has the potential to further delay UAS integration.
Very little literature or coverage ofUAS domestic operations and accidents have
been published and made available to the public at large. As a result, the public
has very little information upon which to form any realistic or reasonable
opinions concerning the integration ofUASs into the NAS and the threat to
public safety that may ensue as a result of this planned action by the FAA and
private. industry. There are many safety related issues that the public are not
aware of that may adversely affect decisions made by the FAA to move forward
with full scale integration of UASs into the NAS.

14
19.Keunhyun Park and Reid Ewing,"The Usability of Unmanned Aerial
Vehicles (UAVs) for Pedestrian Observation",2018
The monitoring of pedestrian activity is challenging, primarily because its
traffic levels are typically lower and more variable than those of motorized
vehicles. Compared with other on-the-ground observation tools, unmanned
aerial vehicles (UAVs) could be suitable for counting and mapping pedestrians
in a reliable and efficient way. Thus, this study establishes and tests a new
method of pedestrian observation using UAVs. The results show that UAV
observations demonstrate high levels of interrater reliability (intraclass
correlation coefficient = 0.99) and equivalence reliability (Cronbach’s α = .97
with on-the-ground counts and .73 with Google Street View). Practical
implications of the new tool are discussed.

20.Dr. Jangala. Sasi Kiran,"A Literature Survey on Digital Image Processing

Techniques in Character Recognition of Indian Languages",2015
Handwritten character recognition is always a frontier area of research in the
field of pattern recognition. There is a large demand for OCR on hand written
documents in Image processing. Even though, sufficient studies have performed
in foreign scripts like Arabic, Chinese and Japanese, only a very few work can
be traced for handwritten character recognition mainly for the south Indian
scripts. OCR system development for Indian script has many application areas
like preserving manuscripts and ancient literature written in different Indian
scripts and making digital libraries for the documents.

21. SSurbhi Jainurbhi Jain and et al.,”Image Enhancement on OpenCV

based on the Tools: Python 2.7”,2017
In the vast area of digital image processing and high resolute transmission
approach, this paper describes the image enhancement techniques which are
based on OpenCV. OpenCV is the latest emerging approach in the area of
image processing. Open CV initially introduced by Intel, which has its own
inbuilt library for image and video analysis. This paper includes three
applications of OpenCV library. The coding of all three approaches is done by
Python 2.6. The first method is Histogram specification of an image in python
language, second technique is live edge detection of a video which is accessed
along with current time using webcam, and the third approach is live face
detection.

15
22. Vivek Kishore Bhanse and et al.,”Face Detection and Tracking Using
Image Processing on Raspberry Pi”,2018
Image processing is nowadays used as a piece of various applications. Confront
area and its following is one of the basic frameworks used as a piece of the uses
of image processing. in this paper we have shown an application for the
improvement of the auto applications with the help of face revelation. The paper
shows the examination how the assurance of the camera impacts the edge each
seconds and respectably the perfect open door for stand up to acknowledgment.
The image processing using OpenCV for face detection, face tracking and its
recognition for automotive application is done here. We have used processor
controller and common USB camera for controlling the electrical motor which
in this way controls the motorized auto application.

23. Sudeshna Bhosale and et al.,”Face Detection and Recognition

Techniques: A Survey”,2018

The biometric is a study of human behavior and features. Face recognition is a

technique of biometric. Various approaches are used for it. Authentication &
Identification has become major issue in today’s digital world. Face recognition
plays a significant role in authentication & identification. In this paper several
existing face detection and recognition approaches are analyzed and discussed.
Each approached is discussed briefly & compared with the other in terms of key
evaluation parameters. As face detection is the elementary yet an important step
towards automatic face recognition, main goal of this paper is to come up with
an approach that is a good candidate for face detection and face recognition.

24. Rudy Hartanto and Risanuri Hidayat,”A Review Paper on Attendance

Marking System based on Face Recognition”,2017

Attendance marking system has been become a challenging, intriguing and

accurately in the real-time system. It is tough to mark the attendance of a
student in the large classroom, and there are many students attend the class.
Many attendance management systems have been implemented in the current
research. However, the attendance management system by using facial
recognition still has issues which allow the research to improve the current
research to make the attendance management system working well. The paper

16
will do a literature review on the previous worked from different researcher has
done on their research paper.

25. Ajay Talele and Aseem Patil,”Detection of Real Time Objects Using
Tensor Flow and OpenCV”,2019

Detecting and recognizing objects in unstructured as well as structured

environments is one of the most challenging tasks in computer vision and
artificial intelligence research. This paper introduces a new computer vision-
based obstacle detection method for mobile technology and its applications.
Each individual image pixel is classified as belonging either to an obstacle
based on its appearance. The method uses a single lens webcam camera that
performs in real-time, and also provides a binary obstacle image at high
resolution. In the adaptive mode, the system keeps learning the appearance of
the obstacle during operation. The system has been tested successfully in a
variety of environments, indoors as well as outdoors.

17
 3.ISSUES AND CHALLENGES

1. Effect of climate:- Weather changes in an area affects the use of drones

2. Most drones are designed to operate at a speed of 20mph ,thus we cannot use
them in an area withhigh wind speed

3. Cost:- Buying a drone fitted with all features needed foryour use maybe very
expensive.

4. Cameras cannot capture when there is fog and rain

5. As image processing needs heavy computations,we requireefficient

processor and GPU.

6.Image processing requires video streaming with high FPS

rate which corresponds to high data transfer.

7. Surveillance in urban canyons is difficult because radars and optical sensors

need line-of-sight visibility, acoustic detectors have very short range, and RF
detectors have low spatial resolution.

8. Navigation in urban setting using GPS can be highly inaccurate due to

multipath errors (especially non-line-ofsight multipath). There needs to be a
backup navigation capability

9. No ground infrastructure and services. No battery charging or swapping

standards.

10. Legislators should follow a property rights approach to aerial surveillance,

explicitly extending to property owner’s rights in their airspace up to 350 feet
above ground level.

18
 4.Motivation,Scope and Problem Definition

The main motivation for the developing of this project is to provide the
better surveillance using these drones so security forces can take quick actions
and they will be also having the proof of security threats through which they can
catch the culprits responsible for it.

These are the several advantages of these drones which motivated for the
development of this project

Advantages:

Drones provide the easier,faster and cheaper method of data collection.

Quiet: A serious disadvantage of helicopters and planes in surveillance is their

noise,highly efficient drone motors allow for discrete almost silent monitoring
and enter into the narrow and confined spaces.

Flexible: They can be armed with night vision cameras and thermal
sensors,allowing them to see what a human eye cant detect.

Easy use: Drones are easy to use,No costly,time-consuming training programs

are needed,security crew can usually learn to plan and implement missions in a
matter of hours.

Real-time monitoring and co-ordination:The real-time co-ordination with the

crew is possible.

The scope of using the drones is unimaginable because of its

versatility,they can be used by industries,government agencies and even it has
been used by many civilians for their hobby projects.We can just modify the
drone for various purposes based on the need at any time (like the drone used
for the border surveillance can be used for the detecting flood severity)

19
These are the several applications of image processing drones:

 Public Safety and Civil Security

 Emergency/Disaster Monitoring and Control

 Traffic and Crowd Management

 Security for Public Events, large events, festivals, concerts, and sports

 Environmental Management

 Data Generation

 Surveying

 Anti-terror operations

 Border surveillance

 Police-related activities

20
 5.STATE DIAGRAM FOR THE PROPOSED SOLUTION

DESCRIPTION:

The General Proposed solution for surveillance drone is shown in the above
image, where

1. The drone turns on and starts flying in the specified region

2. Record the video and stream it using the RTMP server to the surveillance
monitor.

3. Captures the images of unusual and abnormal activities and alert the security
crew by sharing those images and location where it took place.

4. Drone travel around the specified region and return back to land.

21
 ACTIVITY DIAGRAM FOR THE PROPOSED SOLUTION

The operation of drone and its working:

Step1) Initial state: The drone is started with the necessary power supply for
its operation.

22
Step2) Location & altitude drone: The drone is placed at a certain

the geographical area with a particular altitude hold

Step3) Surveillance mode: After the drone has been placed it is kept

in surveillance mode which will continuously monitor the the geographical area
for detecting the abnormality.

Step4) Video streaming: The captured footages with time stamp, geographical
coordinates are continuously directed to the the system in the control room
where the neural network model will process, capture data from these images.

Step5) Abnormality detection: if image processed is not the normal one, then
immediately it alerts the crew regarding the abnormality.

Step6) Verify: The security crew will verify abnormal image and data extracted
from the image and take further actions according to judiciary immediately.

STEPS INVOLVED

Step 1: Stream the drone's video to a computer/laptop (drone -> your computer)

Step 2: Run an object detection model on the streaming video and display
results (on the your computer)

23
Step 3: Train your own object detection model (to detect new kinds of events).

The image processing:

We can also say that it is a use of computer algorithms, in order to get

enhanced image either to extract some useful information.

The classical problem in computer vision, image processing, and machine

vision is that of determining whether or not the image data contains some
specific object, feature, or activity.

The existing methods for dealing with this are by specifying for objects such as
simple geometric objects (e,g., Polyhedron), human faces, printed or hand-
written characters, or vehicles.

24
Recognition: One or several pre-specified or learning objects or object

classes can be recognized, usually together with their 2D positions in

the image or 3D poses in the scene. ·

Identification: An individual instance of an object is recognized.

Examples: identification of a specific person's face or fingerprint,or

identification of a specific vehicle. ·

Detection: The image data is scanned for a specific condition.

Examples: detection of possible abnormal cells or tissues in medical images or

detection of a vehicle in an automatic road toll system. Detection based on
relatively simple and fast computations is sometimes used for finding smaller
regions of interesting image data which can be further analyzed by more
computationally demanding techniques to produce a correct interpretation.

Feature extraction: Image features at various levels of complexity are

extracted from the image data. Typical examples of such features are Lines,
edges and ridges. Localized interest points such as corners, blobs or points.

25
 CONCLUSION

The security threats have been increasing gradually, there is a need for
identifying and delivering the information regarding these threats to the security
forces quickly. So, they can take actions early, we are using the drones which
make surveillance in the particular geographical area and live streaming of the
images to the control room where the captured images are interpreted, analyzed,
processed and gives an alert message the security forces automatically

The goal is to create a low-cost, lightweight unmanned aerial vehicle

capable of surveillance with its implementation of a camera system. This can
reduce the manual power also the auto-detection of abnormalities and unusual
activities will allow the securities to keep the situation under control. The image
capturing system also helps in providing evidence and proofs for unusual
activities took place.

26
REFERENCES

1.SAURAV KUMAR and E.KANNIGA,"LITERATURE SURVEY ON

UNMANNED AERIAL VEHICLE",International Journal of Pure and Applied
Mathematics Volume 119Year: No. 12 2018, 4381-4387
2. Kalpesh R. Dashpute and Nilesh S. bawa,”UAV-Based Traffic Analysis: A
Universal Guiding Framework",Transportation Research Procedia
Year:Volume 22, 2017, Pages 541-550
3.Hanno Hildmann and Ernö Kovacs,"Using Unmanned Aerial Vehicles (UAVs)
as Mobile Sensing Platforms (MSPs) for Disaster Response, Civil Security and
Public Safety", https://www.mdpi.com/journals,Year: 2019, 3(3), 59;
4. Caleb, Nanchen Nimyel, Alfred and Nanpak Albert," Security Of
Unmanned Aerial Vehicles: A Literature Review And Research
Directions",American Journal of Engineering Research (AJER),Year:02-10-
2018
5.Hazim Shakhatreh, Ahmad Sawalmeh, Ala Al-Fuqaha, "Unmanned Aerial
Vehicles: A Survey on Civil Applications and Key Research
Challenges",arXiv:1805.00881v1 [cs.RO],Year:19 Apr 2018
6.Gilles Albeaino, M.Sc. Student, " A SYSTEMATIC REVIEW OF
UNMANNED AERIAL VEHICLE APPLICATION AREAS AND
TECHNOLOGIES IN THE AEC DOMAIN",www.itcon.org - Journal of
Information Technology in Construction - ISSN 1874-4753,Year:: July 2019
7.Ciara Bracken-Roche, David Lyon Mark, James Mansour,"Surveillance
Drones: Privacy Implications of the Spread of Unmanned Aerial Vehicles ".
Surveillance Studies Centre, Queen’s University,Year:April 30, 2014
8. "Literature Review on UAV” ,
http://ludwig.missouri.edu/405/draft/Soper_Intro.htm
9.Anuj Puri, "A Survey of Unmanned Aerial Vehicles (UAV) for Traffic
Surveillance ",Department of Computer Science and Engineering University of
South Florida ,Year: 2018
10.Abdou Fall,"Assistive Drone Technology: Using Drones to Enhance
Building Access ",University of Cincinnati,Year:28-03-2018
11. Truls Hallberg Tønnessen,"Islamic State and Technology – A Literature
Review",Islamic State and Technology ,Year: December 2017
12.Rachel M. Burns,"Unmanned Aerial Vehicles",RAND corporation,Year:
2018

27
13. Isha Kalra, Maneet Singh, Shruti Nagpal,"DroneSURF: Benchmark Dataset
for Drone-based Face Recognition",IIIT-Delhi, India,Year: 2019
14.Vroegindeweij, B.A.," Autonomous unmanned aerial vehicles for
agricultural applications",Research output of Wageningen University &
Research staff,Year: 2014
15.Dr. Markus Kückelhaus,"UNMANNED AERIAL VEHICLE IN
LOGISTICS",DHL Customer Solutions & Innovation ,Year: 2014
16.Eren Unlu,Emmanuel Zenou,Nicolas Riviere," Deep learning-based
strategies for the detection and tracking of drones using several
cameras",Springer link,Year: 24 July 2019
17.Rachel Rhodes, Natalie Spiegel, "Of The Effects Of Unmanned Aircraft
Systems On Seabirds And Marine Mammals",NOAA | Greater Farallones
National Marine Sanctuary,Year:2017
18.Dennis Vincenzi," Public Perception of Unmanned Aerial Systems (UAS): A
Survey of Public Knowledge Regarding Roles, Capabilities, and Safety While
Operating Within the National Airspace System (NAS) ",Scholarly Commons
Citation,Year:8-2013
19.Keunhyun Park, Reid Ewing, "The Usability of Unmanned Aerial Vehicles
(UAVs) for Pedestrian Observation",journals.sagepub.com,Year:October 19,
2018
20.Dr. Jangala. Sasi Kiran,"A Literature Survey on Digital Image Processing
Techniques in Character Recognition of Indian Languages",International
Journal of Computer Science and Information Technologies,Year:May 2015
21.SSurbhi Jainurbhi Jain and et al.,”Image Enhancement on OpenCV based on
the Tools: Python 2.7”,International Journal for Research in Applied Science &
Engineering Technology (IJRASET) ISSN: 2321-9653; IC Value: 45.98; SJ
Impact Factor:6.887 Volume 5 Issue VII, July 2017
22.Vivek Kishore Bhanse and et al.,”Face Detection and Tracking Using Image
Processing on Raspberry Pi”,Publisher: IEEE, 2018 International Conference.
23.Sudeshna Bhosale and et al.,”Face Detection and Recognition Techniques: A
Survey”,International Journal of Advanced Research in Computer and
Communication Engineering Vol. 7, Issue 11, November 2018

24.Rudy Hartanto and Risanuri Hidayat,”A Review Paper on Attendance

Marking System based on Face Recognition”,5th Int'l Conference on Image
Processing, Communication, Engineering and Technology (IPCET-17) Oct. 11-
12, 2017 Bali (Indonesia)

28
25.Ajay Talele and Aseem Patil,”Detection of Real Time Objects Using Tensor
Flow and OpenCV”,Asian Journal of Convergence in Technology Volume V
Issue I,ISSN NO: 2350-1146 I.F-5.11

29