Intelligent Self-Protection Solution Against COVID-19

Abstract

With the ongoing crisis, it is important for every human to protect themselves from the virus infection. Even though the enemy is invisible and looks terrifying, it is very well possible to defend it with simple techniques. One among those techniques is to maintain a safe distance when we encounter another human. But, how do we always keep track of this distance of 6 feet apart can always seem like an illusion and there is a high possibility that we may lose track of our position. In this paper, we propose a system which will help in detecting when a human comes in contact with another person less than the recommended distance. As the solution demands advanced methodologies, the present paper proposes mask RCNN-based deep learning architecture in the computer vision domain. This algorithm is able to draw bounding boxes effectively whenever the person comes closer than the preferred social distance. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.