Covid19-Social-Distancing-Detection

This is a Social Distancing Detector project.

Social Distancing Detector and Monitoring Project, COVID-19 Tracker

This project uses Deep Learning based YOLOv3 Pretrained model for object Detection, OpenCV python library for image processing and Centroid Tracking Algorithm For object tracking. In this project, I am attaching the code for building a Social Distancing Detector to detect if a crowd is practicing Social Distancing or not, using a sample video.

Social Distancing is one such terminology that has gained popularity over the past few months, thanks to COVID-19. People are forced to maintain a sufficient amount of distance between each other to prevent the spread of this deadly virus. Amidst this crisis, I and My Project Team decided to build a simple Social Distancing Detector that could monitor the practice of social distancing in a crowd.

Programming languange & Algorithm used:

• Python
• YOLOv3 model

Technology Used:

• OpenCV (for frame/image processing)
• Deep Learning (Used YOLOv3 Pretrained model for object Detection-(used filter for people indentification only))
• Centroid Tracking Algo (For object tracking)

Dependencies:

• imutils==0.5.3
• numpy==1.18.5
• opencv-python==4.2.0.34
• pkg-resources==0.0.0
• scipy==1.4.1

How to run?

Google Colab Notebook

• PLEASE DOWNLOAD THE YOLOv3 MODEL FROM BELOW LINK AND KEEP ALL THE DOWNLOADED FILES INSIDE THE SAME FOLDER

  • Download YOLOv3 Model

• clone the repository to your local machine

• navigate to this cloned directory

• from the terminal install dependencies using these commands:

  • python -m pip install opencv-python
  • from scipy.spatial import distance as dist
  • import numpy as np
  • import argparse
  • import imutils
  • import os

• after installing the dependencies run the social_distancing_config.cpython file from terminal using this command:

  • python social_distancing_config.cpython

• To analyze the different sample videos & Execute, Follow this:-

  • example:
    python social_distance_detector.py --input VIDEO1.mp4 --output OUTPUT1.mp4 for first Video
    python social_distance_detector.py --input VIDEO2.mp4 --output OUTPUT2.mp4 for second Video
    and so on.

RESULTS OF MODEL VIDEO ON TESTING:

1.

Video1 Input:-

Video1 Output:-

2.

Video2 Input:-

Video2 Output:-

This is Computer Vision And Image Processing project which can be used for monitoring social distancing in Lockdown & to fight against COVID-19 a.k.a. the Corona Virus.

Fell free to contribute to this project by providing more sample videos, your contribution will be appreciated.

Thank You!