Sonali Suri
CSE 261
Fall 2020

Di-Mask : COVID Mask tracker and distance detector

Machine learning (ML) is a technology used on alarge scale and helps us change the world. Machine learning focuses on developing computer programs that can access dataand use them to learn for themselves. The learning process begins with observations or data, such as examples, direct experience,or instruction, to look for patterns in data and make betterdecisions in the future based on the examples that we provide.The primary aim is to allow the computers to learn automatically without human intervention or assistance and adjust actions accordingly. On the other hand, visualization helps us in a better understanding of data and results. In today’s time, COVID prevention has become an important concern for everyone. In this project, I propose Di-Mask: A Realtime Distance Estimation and Mask Detection Pipeline, which uses Machine Learning to help prevent spread of COVID-19

Images

Fig.1 - Mask detection and distance tracker (in inches)	Fig.2 - Mask detection for multiple people	Fig.3 - Mask detection with fancy mask
Fig.4 - Mask detection with fancy mask	Fig.5 - Mask detection in a crowd

Demo Video with mask detection and distance calculation

User's Guide for Di-Mask

The application runs on live video stream. Both the versions for detecting masks through Viola Jones and detecting masks through Vision API can be found in the Github Repo mentioned below. User needs to just start the live stream by clicking the start button and the output will be displayed for each frame on the adjacent camera.

Source code

Github repo

Paper

Paper link