Real-time Facemask Detector using Deep Learning and Raspberry Pi

Abstract

Medical staffs wear face masks to prevent the spread of the disease. Nowadays, with the coronavirus pandemic everyone must wear a facemask for the same reason. When a person near to you coughs, talks, sneezes he could release germs into the air that may infect you or anyone nearby. Wearing a facemask is a part of an infection control strategy to avoid and eliminate cross-contamination. Even so, people are getting tired of wearing facemasks or they are not conscious enough of the seriousness of the actual covid19. In this paper, we propose a facemask detector based on IoT embedded devices and deep learning algorithm. Our main goal is to warn people in real-time if they are not wearing a facemask or they are not wearing it correctly. The proposed solution generates loud vocal alerts after detection disrespect of facemask wear in real-time for a fast reaction. To have the most efficient detector in real-time we tested the facemask detection model using various versions of the Raspberry Pi and NCS2. As a result, the facemask detector works perfectly on powerful devices, however its performance decrease in realtime using less powerful devices such as an old version of the Raspberry Pi.