AI Based Covid-19 Solution Compliance

• 

  Diagramatic Moqup

Inspiration :

World Health Organization guidelines says that the only way to prevent covid-19 spread is by maintaining social distancing, wearing mask and screening out of people having covid symptoms such as fever and conjunctivitis. The administration does not have enough workforce to handle the public manually, So we decided to make such monitor systems using AI to help them and contribute the best we can.

What it does

How we built it

As AI is the most leveraging technology, we choose it to make our Compliance solution to monitor such prevention factors and alarm the concerned authorities whether people are following the norms or not. Our Compliance consists of state-of-the-Art screening of people carrying corona virus symptoms such as fever, redness in eye, not wearing mask and not following social distancing

Challenges we ran into

1. Calculating and calibrating the distances between each and every individual while building our AI based social distancing system.
2. Deployment and calibration of open CV and other framework on Jetson Nano board.
3. Deciding the smart value of Threshold for red colour while detecting the conjunctivitis or any other redness in eyes.

Accomplishments that we're proud of

Contrary to others, this system is scalable and can detect multiple streams in optimal time. Can be deployed on edge and cloud both along with battery backup(12 hrs max.) The USP of this project is that it can detect multiple people (around 100) in one frame.

What's next for AI Based Covid-19 Solution Compliance

Making RFID access control systems CONTACTLESS : We will use this tech to enhance the pre existing RFID based access control systems contactless. This Will also provide count of persons following norms and who are not, in the monitored area.

Built With

• computervision
• deeplearning
• kinter
• python
• tensorflow