BATCH

178

Advanced Video
Surveillance System By
using Computer Vision
Under the guidance of
Dr. E., Anna Devi M.E., Ph.D.

Presented by: -
CH. SRINADH (39130090)
CH. PRAVEEN KUMAR (39130091)
 GUIDE FEEDBACK FORM
BATCH 178

NAME :- CH. SRINADH NAME :- CH. PRAVEEN KUMAR

REG.NO :- 39130090 REG.NO :- 39130091

BRANCH :- ECE BRANCH :- ECE
SECTION :- A2
SECTION :- A2

GUIDE NAME : - Dr. E., Anna Devi M.E.,

Ph.D.

20XX 2
INDEX

INTRODUCTION LITERATURE SURVEY DESIGN AND PAPER PUBLISHING &

EXPLAINATION SOURCES DEVELOPMENTS PLAGIARISIM

Sathyabama institute of science and technology 2023 3

PROJECT WORKFLOW

OpenCV FACE REGISTRATION

Project Manager Py Manager

Web cam Skimmage Moving detection

Compactable Detection Computer vision

Noise and object

tKinter
identification
Python Resources
screen detection

Contoso business plan 20XX 4

 Project summary

By using sophisticated algorithms and machine An advanced video surveillance system that Our product cost is low, which
uses computer vision is a powerful tool for
learning techniques, these systems can analyze gives us a market advantage.
enhancing security in a variety of settings,
video footage from multiple sources, detect
including public spaces, commercial buildings,
objects of interest, track their movements over
and critical infrastructure.
time, and identify potential threats or unusual

behavior. This can help security personnel to

respond more quickly and effectively to potential

security incidents, improving overall safety and

security.

Contoso business plan 20XX 5

 Opportunities
Software Installment Costs
It is compactable and easy to install in an usable Loss of productivity costing consumers thousands
laptop or a computer. of dollars 

Emergency or temporary set up. Usability

It can be set up with in a seconds and user can use their Customers want something that is easy to use
laptop or computer as surveillance with their web cam only.

Designing of software.
It was designed by most user friendly and easy
to understanding language python

Contoso business plan 20XX 6

 Project overview

Contoso business plan 20XX 7

 Project concept
The concept of advanced video surveillance systems using
computer vision is based on the idea of using artificial intelligence
and machine learning to improve security and safety in various
settings. By analyzing and interpreting visual data from cameras
and other sensors, these systems can automatically detect and track
objects of interest, identify potential threats or unusual behavior,
and generate alerts for security personnel to take appropriate
actions. This can help to reduce the burden on human operators and
improve the overall effectiveness of security measures.

Contoso business plan 20XX 8

Goals and objectives

Designing blueprints Run focus on errors

Jan 2023 Mar 2023

2023 JAN FEB MAR APR MAY JUN JUL AUG SEP OCT NOV DEC

2022 JAN FEB MAR APR MAY JUN JUL AUG SEP OCT NOV DEC

Launch design
Test design Gather feedback RESEARCH WORK
Feb 2023 Sept 2022 Dec 2022
Apr 2023

20XX Contoso business plan 9

Project Analytics

Key metrics Comparison of compression techniques

COMPARISON OF STORAGE MEMORY (IN MB) $80
Recording on $70
Normal
Duration motion
recording
(in sec.) detection $60
(MB)
(in MB)
$50

05 13 6 $40

$30
15 31 9
$20

$10
45 39 11
$0
1 2 3 4
55 89 12

Contoso business plan 20XX 10

 Literature survey
Sivakumar, Swetha, and R. Gomati Bhavani. "Image Processing Based System for
Intrusion Detection and Home Security Enhancement." In 2018 3rd IEEE International
Conference on Recent Trends in Electronics, Information & Communication
Technology (RTEICT), pp. 1676-1680. IEEE, 2018

This paper combines the above two methodologies and proposes a simple, cost effective, two-
layered system. The system is proposed for the main doorway of the property and has been
designed and demonstrated already. In the above system, an Arduino controller communicates
with sensors and image processing tools of MATLAB to authorize entry using GSM module.
This makes sure that only personnel recognized by owner database are given permission,
limiting intrusions to a large probability.

Contoso business plan 20XX 11

LITERATURE SURVEY

Bhanse, Vivek Kishor, and M. D. Jaybhaye. "Face Detection and tracking using Image
processing on Raspberry Pi." In 2018 International Conference on Inventive Research in
Computing Applications (ICIRCA), pp. 1099-1103. IEEE, 2018.

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. the viola-jones estimation for stand up to acknowledgment using ad boost library in this way
structure relies upon adaboost computation and changed works faces hear-like highlights in the item part we have
used python vernacular with open cv reinforce for the face distinguishing proof using haar course records gave
by intel open source. we have shown the results on layout consistently impact on stand up to distinguishing
proof.Bhante
Contoso business plan 20XX 12
LITERATURE SURVEY
Kakatiya, R., Limos, R., Mangalam, S., Pillai, M. and Nikam, S., 2019, June. Ai based
automatic robbery/theft detection using smart surveillance in banks. In 2019 3rd International
conference on Electronics, Communication and Aerospace Technology (ICECA) (pp. 201-204).
IEEE.
Analyzing videos, a part of deep learning is one of the most basic problems of computer vision and
multi-media content analysis for at least 20 years. The job is very challenging as the video contains a
lot of information with large differences and difficulties. Human supervision is still required in all
surveillance systems. New advancement in computer vision which are observed as an important trend
in video surveillance leads to dramatic efficiency gains. We propose a CCTV based theft detection
along with tracking of thieves. We use image processing to detect theft and motion of thieves in
CCTV footage, without the use of sensors. This system concentrates on object detection. The security
personnel can be notified about the suspicious individual committing burglary using Real-time
analysis of the movement of any human from CCTV footage and thus gives a chance to avert the
same.

Contoso business plan 20XX 13

 Designing and Development
1.Requirements Analysis: In this stage, are
the
key requirements of the system
identified
needs of based
the on the specific
environment. This security
involves
determining the number and type of cameras
or sensors
needed required, video
for real-time the processing
analysis, andpower
the
types of objects or events to be detected.
2.System Architecture: Once the
requirements are identified, the
architecture is designed. This includes system
selecting the hardware and software
components needed to support the system,
such as cameras,
machine learning video processing units, and
algorithms.
3.Algorithm Development: The algorithms
used for object detection, tracking, and
event
This detection
may involve are developed and tested.
using pre-existing
algorithms or developing
to the specific requirementsnew ones
of the tailored
system.

Contoso business plan 20XX 14

 Key issues
It is necessary to make use of automatic video analysis technologies for
developing smart surveillance system which can aid the human operator in
both detecting and reacting to potential threats.

The internet and wireless broadband infrastructure is becoming robust

enough to permit excellent remote video surveillance.

With advances in hardware and software technology, and the emergence of

ubiquitous internet infrastructure and wireless networks with broadband
capability, it is now possible to design and build a networked video
surveillance system that can do an excellent job of remote video
supervision from anywhere and at any time.

The requirements of a video surveillance system differs in important ways

from CCTV, NVR’s and DVR’s.

Smart Video Surveillance System(SVSS) provides video-based object

analysis capabilities.

Contoso business plan 20XX 15

 Face analyzing

Contoso business plan 20XX 16

 Noise and Motion Detection

Contoso business plan 20XX 17

 Project updates
Monitor Detecting

Contoso business plan 20XX 18

 Algorithm running

Contoso business plan 20XX 19

 haarcascade_frontalface_default

Contoso business plan 20XX 20

 Object
detection

Contoso business plan 20XX 21

 In & Out persons Data

Contoso business plan 20XX 22

 20XX

Storing the
output data
with Registered
faces
Contoso business plan 23
 Paper publishing & Plagiarism

Contoso business plan 20XX 24

 Paper publishing & Plagiarism

Contoso business plan 20XX 25

 Thank you
CH. SRINADH
(39130090)
CH. PRAVEEN KUMAR
(39130091)

Contoso business plan 20XX 26