Anti-COVIDnet

How Does it Work?

1. Social Distancing Analyzer

   In this step, social distancing detection logic is applied to any video source and the frames that record violations are extracted in real time which are instantly uploaded to the cloud storage. These images are displayed on the dashboard. The system gives instructions over to the IoT device to instruct people violating norms.

   

2. Face mask detection

   This module detects whether a person is wearing a mask or not. The feed input to the system is analysed for people not wearing face mask. The violated frames are uploaded to the cloud storage which can later accessed whenever required. The system gives instructions over to the IoT device to instruct people violating norms.

   

3. Thermal Screening

   Thermal screening module uses a thermal scanning camera that processes the input stream to identify people having temperature greater than a threshold value. Depending on the requirement of the location, automatic instructions can be delivered using IoT devices.

Now one of the most prominent features of Anti-COVIDnet is preventing such violations from occurring in the first place. Our system keeps track of how many violations occur at various places and then accurately analyses which areas could prove to be risky zones in the offices/colleges and then alerts the gathered crowd in that area instantly to disperse and follow the social distancing norms.

All these features combined make the offices/colleges/malls which have not yet opened a safer place instantly.

Features

Real-time

The system is entirely real-time with neglible latency

IoT integration to automate the system

IoT devices can be used to deliver automatic instructions over speakers

Cloud support

Firebase storage and firestore is used to store data for better management and remote access

Privacy centered

No personally identifiable information is either stored or used without user's consent

Algorithmic Efficiency

The application stands out in comparison with other similar applications

Demo

Built with

• Python
• Django
• HTML
• CSS
• JavaScript
• React JS
• Firebase

Installation

Setting up Anti-COVIDnet

STEP 1: Create a Virtual env to contain all your packages safe

conda env create -f conda-gpu.yml
conda activate tracker-gpu

STEP 2: Install all the requirements

pip install -r requirements.txt

STEP 3: Set up Nvidia Driver for GPU (only if you have not set it up already)

# Ubuntu 18.04
sudo add-apt-repository ppa:graphics-drivers/ppa
sudo apt install nvidia-driver-430
# Windows/Other
https://www.nvidia.com/Download/index.aspx

STEP 4: Download offical Yolov3 weights

For Linux: Let's download official yolov3 weights pretrained on COCO dataset.

# yolov3
wget https://pjreddie.com/media/files/yolov3.weights -O weights/yolov3.weights

For Windows: You can download the yolov3 weights by clicking here then save it to the weights folder.

STEP 5: Run load_weights.py

python load_weights.py  

STEP 6: Initialising the Dashboard

cd ./Anti-COVIDnet-Dashboard
npm install
npm start

The dashboard can be checked out on "http://localhost:3000" once the development server starts.

STEP 7: Activate Anti-COVIDnet Scripts

# Server
python manage.py runserver

Authors

• View all contributors

Support

Please open an issue for support.

Contributing

Please contribute using GitHub Flow. Create a branch, add commits, and open a pull request.

License

This project is licensed under the GPL-3 License - see the LICENSE file for details.

Let us know your thoughts, we're open for ideas!

Feel free to add / contribute features.

If you're interested in this project, feel free to drop us an email on yashsonar213@gmail.com or on Telegram

It's time to re-open,
Because we have had enough!