Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 16

Automatic

Video
Surveillance
System
Objective
The objective is to build an effective system which can
be used across different domains and technologies. The
system is used to Detect Human intervention and breach
security in personal or commercial property of the user in
real time using Artificial Intelligence and IOT.

Surveillance is an integral part of security and patrolling,


For the most part, the job entails looking out for
something undesirable to happen.
Hardware & Software
► System
► dual core or higher
► RAM Required
► 1 GB or More than 1 GB
► OS
► Windows 7 Service pack1 or higher
► Tools
► .Net Frame Work 4.5
► SQL server user interface express
The Problem
Currently the Surveillance systems can keep the video recording of homes, offices,
banks, But that is useful only after incident happens.
No Real time Updates are provided when there is a breach in real time.

Just imagine, You’re sleeping and someone breached your security and stole money or
goods. Or consider you’re out of town for some days and there is a robbery at your
home. So after sometimes you will get updated about the breach at your place.

There are some companies which provides smart surveillance system but for that we
need to update whole bunch of hardwares and that makes huge cost.
What If...
Wouldn’t life be much simpler if there was something that could do
the “watching” for us? With the advancements in technology over the
past few years, we could automate the above tasks by Automating
Surveillance System.

What if...You get real time updates when someone enters in your
property in your absence.

Video surveillance has found applications in many fields,


primarily the detection of intrusion into secure premises and the
detection of theft or other criminal activities.
The Solution
An AI featured security system which have real time
monitoring and alert security system with no extra
installation.

When any human activity is detected, user will get


updated immediately in real time with Mobile
Notification along with a short video clip.
System Architecture
How AI Detects Humans
Within the field of Computer Vision, the sub-discipline called
“Object Detection” involves processes such as identifying
the objects through a picture, video or a webcam feed.

Object recognition is a general term to describe a collection


of related computer vision tasks that involve identifying
objects in digital photographs.

Input an image / frame with one or more objects and Output


one or more class label for each detections.
Implementation
When a computer sees an image (takes an image as input), it will see an array of pixel values. Depending on the resolution and
size of the image, it will see a 32 x 32 x 3 array of numbers. Each of these numbers is given a value from 0 to 255 which
describes the pixel intensity at that point.

The idea is that you give the computer this array of numbers and it will output numbers that describe the probability of the
image being a certain class.
What we want the computers to do ?
Now that we know the problem as well as the inputs and outputs, let’s think about how to approach this. What we want
the computer to do is to be able to differentiate between all the images it’s given and figure out the unique features that
make a person a person.

The architecture is analogous to that of the connectivity pattern of Neurons in the Human Brain and was inspired by the
organization of the Visual Cortex.
Feature Extraction
Now that we know the problem as well as the inputs and outputs, let’s think about how to approach this. What we want
the computer to do is to be able to differentiate between all the images it’s given and figure out the unique features that
make a person.

The architecture is analogous to that of the connectivity pattern of Neurons in the Human Brain and was inspired by the
organization of the Visual Cortex.
Classification

After the feature learning part of CNN, the classification task is performed by the final layer
of a CNN that is a feedforward dense network with one or more hidden layers. The output
layer has a Softmax activation function which provides probability values of image being a
certain class.
Real Time Alerts !!!

As soon as any human is detected, the


system sends SMS alert immediately with a
short video clip of around 10 seconds to the
user.
Future Scope
- Possible to make SaaS which gives alert system with integrated hardware
solution.

- System which provide integrated Alert system.

- System which provides more accurate results with faster detections.


Biblography
- Youtube
- Stackoverflow
- Google
- Tutorials point
- W3school
- Tutorials
- Wikipedia
- Dzone
Thank You
With a high number of real world use
cases, Artificial Intelligence will surely
play an important role in making
security systems more better.

You might also like