Download as pdf or txt
Download as pdf or txt
You are on page 1of 3

ABSTRACT

Social distancing has been proven as an effective measure against the spread of the infectious
COronaVIrus Disease 2019 (COVID-19). However, individuals are not used to tracking the
required 6-feet (2-meters) distance between themselves and their surroundings. An active
surveillance system capable of detecting distances between individuals and warning them can
slow down the spread of the deadly disease.

While millions of people are staying at home to help flatten the curve, many customers in the
manufacturing and pharmaceutical industries are still having to go to work everyday to make
sure our basic needs are met.

To help ensure social distancing protocol in their workplace, In this project an AI-enabled social
distancing detection tool that can detect if people are keeping a safe distance from each other by
analyzing real time video streams from the camera.

Methods of Social Distancing – Cancellation of events


Which involve large numbers of people gathering Together, such as

1. Closure of Community Facilities


2. Closure of non-essential workplaces
3. Closure of schools
4. Closure of colleges and universities
5. Self-Shielding
6. Individuals limit face-to-face contacts
7. Individuals avoid public places
8. Individuals avoid public transport

The demos below will help to visually explain the approach that consists of three main steps:

1. Detect the humans in the frame with yolov3 convolutional neural network.
2. Calculate the distance between all the instances of humans detected in the frame.
3. Classify the determined distances as 'Alert' or 'Ok' for social distancing.

Existing system:

As most of the countries are facing problems with covid 19 pandemic there is a need for effective
systems which need automatic alerting systems. In the existing system there are manual
authentication methods and advertising methods to maintain guidelines which are not followed
by people.

Disadvantages:

Using normal advertising methods it is not easy to follow guidelines.

Changes of increasing Covid cases.


Proposed system:

Proposed system users machine learning methods to detect users form images, videos and live
camera and then use opencv library to detect distance between each user using distance
calculation algorithm and raise alarm and detect each user and show in red and green colour.

Advantages:

The platform generates notifications elegantly

Rapidly finds the image recognition.

Software Hardware Requirements:

HARDWARE REQUIREMENTS:

⮚ System : Pentium IV 2.4 GHz.

⮚ Hard Disk : 100 GB.

⮚ Monitor : 15 VGA Color.

⮚ Mouse : Logitech.

⮚ RAM : 1 GB.

SOFTWARE REQUIREMENTS:

⮚ Operating system : Windows XP/7/10

⮚ Coding Language : python

⮚ Development environment : Anaconda

⮚ Libraries : OPencv, numpy


⮚ IDE : Visual studio code

You might also like