You are on page 1of 14

Social Distancing

Detector in covid 19

Presented by:
Shaikh Ruksana
Jyoti Ashakiran
Salunke Nikita
Kore Priyanka
Content
Introduction
Motivation
Methodology
Proposed System
Algorithm
Advantages
Applications
Conclusion
Reference
Introduction

COVID-19 has completely changed the worlds view on


pandemics with direct consequences to global health
and economy.
During this ongoing COVID-19 pandemic, many
government have implemented various social
distancing measures such as travel restriction, border
control, closing public places, and warning their
citizens to keep a 1.5-2 meters distance from each other
when they have to go outside.
Motivation
The main safety measure suggested by WHO is
maintain Social Distance with others to reduce the risk
of infection when they cough, sneeze or speak.
In the current scenario the only system having to
maintain the social distance in public place is
survillance system like cctv which has to be monitored
by the human.
So we selected this project to bring automation in
social Distance Monitoring.
Methodology
Social Distancing Detector 3 steps

Step 1:
Apply object detection to detect all people
(and only people) in a video stream.
Step 2:
Compute the pairwise distances between all detected
people.
Step 3:
Based on these distances, check to see if any two people
are less than N pixels apart.
1. Pedestrian detection:
An open source object detection network based on the
YOLOV3 algorithm was used to detect the pedestrian in the video frame.
2. Camera view Calibration:
The camera is captured at fixed angle as the video frame.
The video frame was treated as perspective view are transformed
into a two dimensional top-down view for more accurate estimation of
distance measurement.
3. Distance Measurement:
Depending on the preset minimum distance, any distance less
then the acceptable distance between any two individual will be indicated
with red lines that serve as precautionary warnings.
Proposed System
 In this proposed system we will see the detailed explanation of how we
can use python, computer vision and deep learning to monitor social
distancing at public places and workplaces.

 To ensure social distancing protocol in public places and workplace,


the social distancing detection tool that can monitor if people are
keeping a safe distance from each other by analyzing real time video
streams.

 This video streams are from the camera, monitoring people at


workplaces, factories,shops we can integrate this tool to their security
camera system and can monitor whether people are keeping a safe
distance from each other or not.
Algorithm
Start real time video recording
Processing of data in video using deep neural network
Detection of every person present in video
Count the number of people in video
Set minimum distance value
Calculation of distance using euclidean distance
formula
Provide an alert if minimum distance is not followed.
Advantages
Limit opportunities to come in contact with
contaminated person.
Provide alerts if specific distance not maintained.
Provides safety.
Easy to operate.
Application
Elevators
Offices
Organizations
Malls and Multiplex
Educational institutes
Restaurants
Banks
Conclusion
Using machine learning and AI it is possible to
estimate social distancing accurately.

The system can control death rate and spread of


corona by ensuring social distancing in public places.
Referance
https//www.cdc.gov/coronavirous/209
https://ieeexplore.ieee.org/abstract/document/
9243478
Thank You

You might also like