Surveillance System For COVID Prevention Using Machine Learning

Project Title

Surveillance System For COVID Prevention Using Machine Learning

Project Area of Specialization Artificial IntelligenceProject Summary

Deep learning is one of the emerging fields in computer science that is being used to make intelligent systems that are benefiting Mankind at various levels and different fields. COVID-19 is a deadly pandemic that should be prevented by properly following SOPs. We will be developing an intelligent system that will help the governing bodies in implementation of the prevention strategies among people.

The two prevention methods that our system will detect our:

1. Detecting people who are not wearing mask. The CCTV cameras will be installed on entrance of  Universities, Offices, Libraries and other public places. Our system will detect that whether the person who is entering is wearing a mask or not. This will be implemented using computer vision and deep learning.
2. Detecting people who have gathered in groups without maintain social distance. The CCTV cameras will be installed in crowdy places such as cafeteria, coli doors, sitting areas etc. Our system will detect the groups and measure the distance between people whether they are maintaining the right distance between them or not.

Moreover we will be developing a web app that will help us in monitoring and managing this system.

Project Objectives

This project has following objectives:

• Facemask Detection using CCTV Cameras installed at suitable places for maximum detection
• Web app to monitor Real Time Data, Manage Alerts, Generate Reports
• Prevention of spreading of covid by gatherings by detecting gatherings in which safe distance between people in not maintained

Project Implementation Method

Technologies Used

• OpenCV - a library of programming functions mainly aimed at real-time computer vision.
• Tensor Flow -  open-source software library for machine learning.
• Keras - an interface for the TensorFlow library.
• Python
• Flask - a lightweight WSGI web application framework

Neural Network

• YOLO V3 - latest latest variant of a popular object detection algorithm YOLO – You Only Look Once
• Faster RNN - object detection architectures that uses convolution neural networks like YOLO (You Look Only Once) and SSD ( Single Shot Detector)

Benefits of the Project

Benefit of our project is to provide the governing bodies an intelligent system that will help them in preventing COVID-19 and save lives of people as we have already lost thousands of lives because of this deadly pandemic.

Technical Details of Final Deliverable

Following are the technical details of our project:

1. Design a user-friendly Web App where we can see the results, real-time video, manage cameras generate reports.
2. Our system will differentiate between people on the basis of facemask.
3. Our system will detect grouping of people.
4. Our system will detect the distance between people who are in groups and tell whether they have maintained social distance or not.

Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther Industries Health , Security Core Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Good Health and Well-Being for PeopleRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	8000
CCTV Camera	Equipment	2	4000	8000