IOT enabled Computer Vision Based Social Distancing Detector

Social distancing has been proven as an effective measure against the spread of the infectious and contagious disease (COVID-19). However, individuals are not used to tracking the required 1-meter distance between themselves and their surroundings. An active surveillance system capable of detecting

Project Title

IOT enabled Computer Vision Based Social Distancing Detector

Project Area of Specialization

Internet of Things

Project Summary

Social distancing has been proven as an effective measure against the spread of the infectious and contagious disease (COVID-19). However, individuals are not used to tracking the required 1-meter distance between themselves and their surroundings. An active surveillance system capable of detecting distances between individuals and warning them can slow down the spread of the deadly disease.

Here we propose a Computer vision based Social Distancing Detector.

Computer vision is a field of artificial intelligence that trains computers to interpret and understand the visual world. Using digital images from cameras and videos and deep learning models, machines can accurately identify and classify objects and then react to what they see. Using Computer Vision we will implement a real time surveillance camera that would detect the required 1-meter distance between the individuals as well as detect whether an individual is wearing a mask or not.

Project Objectives

The impact of the COVID-19 pandemic is drastically changing the lives of people all around the world. Educational institutions, banks, offices, shopping malls, restaurants were closed, exams and many important events worldwide postponed, the usual health information services are limited, socializing with friends and wider family is highly discouraged and in some places even punishable, with passing time things are getting back to their places and people all around are being guided to follow Standard Operating Procedures (SOPs) which are step by step instructions compiled by the specific organizations. But the COVID-19 pandemic is still there on much a decreased level. Living in these circumstances can be tough for people for their social, physical and mental wellbeing.

Therefore by installing the social distancing detector we can minimize the spread of this deadly disease.

Project Implementation Method

The steps to build a social distancing detector include the following methodology:

• We will install a surveillance camera that would record a real time scenario.
• With the feature of object detection we will detect all the people in the stream.
• Compute the pair wise distances between all detected people.
• Based on these distances we check the required distances among the people and also detect whether the person is wearing a mask or not.

If the distance is less than one meter between the individuals, it will be detected by forming a red square around the individual, on the other hand if the distance meets the requirement a green square will be formed around the individual. 

Benefits of the Project

By installing the social distancing detector we can minimize the spread of this deadly disease.They can be used in Educational Institutes, Offices, Banks, Hospitals, Airports, almost everywhere and we help in creating a safe environment. If we take an example of a University, and we install these social distancing cameras in corridors so it would help us know whether the students and staff are maintaining the social distancing or not, also we would be able to know if they are wearing a mask or not. So this would help us warn the violators of the Standard Operating Procedures (SOPs).

Same goes for other places too. It would help us in the same way if we install them somewhere else.

Technical Details of Final Deliverable

The Final Project will be a Social Distancing Detector that will consist of a Camera and Raspberry pi. The Camera will record the live stream and Raspberry Pi will first detect the individuals in the live stream and then find the distance between the individuals and whether they are wearing the mask or not. If the person is not following the SOPs a red box will appear around him/her on a remote screen. 

We will code the Raspberry Pi in Python using the Computer Vision Library named "OpenCV" for human detection and mask detection. All the deep learning processing will be done by Raspberry Pi and then display the output on a Remote Screen over the Internet. 

Final Deliverable of the Project

HW/SW integrated system

Core Industry

IT

Other Industries

Telecommunication

Core Technology

Internet of Things (IoT)

Other Technologies

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com