Vidya Vikas Institute of Engineering and Technology

VIDYA VIKAS INSTITUTE OF ENGINEERING
AND TECHNOLOGY
#127-28, Bannur Road, Aalanahally Post, Mysuru-570028
DEPARTMENT OF INFORMATION SCIENCE AND

ENGINEERING
Internship Presentation
on
“Background Subtraction on Real time Video
by
Sanjana S Urs-4VM19IS035
Internal Guide External Guide

Prof. Vjayananda V Madlur Suresh Kumar
Assistant Professor
Dept of ISE
Project Manager
Take it Smart
PVT.LTD
•About the Company
•Introduction – (About the topic,/Objective/Problem
Statement)
•Design/Block Diagram
Contents •Methodology
•Implementation
•Requirements
•Reflection
•Results & Conclusion
•References
About the company
• Take It Smart (Opc) Private Limited is a 1 year 7 months old, One

Person Company incorporated on 28 Jul 2021.
• It involves under in Business Activity Class / Subclass.
• Activities like Maintenance of websites of other firms/ creation of
multimedia presentations for other firms etc.], It Comes Under
Division COMPUTER AND RELATED ACTIVITIES .
Introduction
OBJECTIVES
 Background subtraction is a way of eliminating the background from image. To achieve
this we extract the moving foreground from the static background.
 Background subtraction is a major preprocessing step in many vision based applications.
Problem statement
 In the cases like visitor counter where a static camera takes the number of
visitors entering or leaving the room, or a traffic camera extracting
information about the vehicles etc. In all these cases, first you need to
extract the person or vehicles alone. It will be difficult to extract the
information without subtracting the background.
Proposed solutions
• In order to overcome this drawback, we have developed a background

subtraction on Real Time vedio using OpenCV
Background modeling consists of two main steps:
• 1.Background Initialization;
• 2.Background Update.
System Architecture
Library
OpenCV,NUMPY
Input Real Time

Camera output- Binary
Laptop Python view
Background
subtraction Algorithm
Methodology
• OpenCV is a handy Python library that allows us to do a number of

critical operations. One of the functions of this library includes the
creation of Background Subtraction.
• Create Background Subtraction using Real Time Camera
• Define the MOG function
• Adjust the position of the Camera to suit your content
• Press Letter ‘b’ in keyboard to capture Background.
Implementation
BackgroundSubtractorMOG
It is a Gaussian Mixture-based Background/Foreground Segmentation Algorithm.It uses a
method to model each background pixel by a mixture of K Gaussian distributions (K=3 To 5).
Machine Learning
Machine learning is the study of computer algorithms that improve automatically through
experience. It is seen as a subset of artificial intelligence. Machine learning algorithms build a
mathematical model based on sample data, known as "training data", in order to make
predictions or decisions without being explicitly programmed to do so.
Python
Python is an interpreted, object-oriented, high-level programming language with dynamic
semantics. Its high-level built in data structures, combined with dynamic typing and dynamic
binding, make it very attractive for Rapid Application Development.
Requirements
Hardware Requirements
 Computer – Processor, high speed is preferred. 32/64 - bit
 RAM 4GB
 Hard disk – Free space of 5GB
 Laptop built-in Camera
Software Requirements
 Python 3.7
 Open CV tool
 OS – Windows 7 / 8 / 10, 32/64 – bit.
Reflection
• My internship experience was very advantageous. In that one month duration I learnt so many
skills .
• Take it Smart has offered me opportunities to learn and develop myself in many areas.
• A lot of tasks and activities that I have worked on during my internship are related with what
I’m studying now.
Results and conclusion
• After working with this project, I got to understand more about the technologies with real time
examples.
• Background Subtraction method can be used in Vehicle counting applications in highway.
• Intruder Detection can be implemented using Background Subtraction Algorithm.
Input of stored video output of stored video subtraction
References
[1] Henry et al., "Anomaly Detection in Videos Recorded by
Drones in a
Surveillance Context", International Carnahan Conference on
Security Technology (ICCST), Madrid, 2017.
[2] Mohammad Farhadi et al., “AAD: Adaptive Anomaly

Detection through traffic Surveillance videos”, arXiv:1808.10044,
2018.
Thank You

Vidya Vikas Institute of Engineering and Technology

Uploaded by

Copyright:

Available Formats

Vidya Vikas Institute of Engineering and Technology

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Vidya Vikas Institute of Engineering and Technology

Uploaded by

Copyright:

Available Formats

VIDYA VIKAS INSTITUTE OF ENGINEERING

DEPARTMENT OF INFORMATION SCIENCE AND

Internal Guide External Guide

•Introduction – (About the topic,/Objective/Problem

•Results & Conclusion

• Take It Smart (Opc) Private Limited is a 1 year 7 months old, One

• In order to overcome this drawback, we have developed a background

Input Real Time

• OpenCV is a handy Python library that allows us to do a number of

[2] Mohammad Farhadi et al., “AAD: Adaptive Anomaly

You might also like