Estimating social distance in public places for COVID-19 protocol using region CNN

Abstract

The Coronavirus disease has spread throughout the world and its fear has made people to be more cautious in public places. Since precautionary measures are the only reliable protocol to defend ourselves, social distancing is the only best approach to defend against the pandemic situation. The reproduction number i.e. R0 factor of COVID-19, can be slowed down only through the physical distancing norms. This research proposes a deep learning approach for maintaining the social distance by tracking and detecting the people present indoor and outdoor scenarios. Surveillance video is taken as the input and applied into you only look once (YOLO) V3 algorithm. The persons in the video are identified based on the segmentation algorithm present within the framework and then using Euclidean distance the image is evaluated. The bounding box algorithm helps to segregate the humans based on the minimum distance threshold. The proposed method is evaluated for images with peoples in the market, availing essential commodities and students entry inside a campus. Our proposed region-based convolutional neural network (RCNN) algorithm gives a better accuracy over the traditional models and hence the service can be implemented in general for places where social distancing is mandatory.