ABSTRACT
In the pandemic of COVID-19, the indoor physical distancing protocol has been one of the recommendations for people to avoid close contact with each other in order to prevent contagious clusters. This paper proposes an end-to-end camera-based human physical distancing recording system for an indoor environment, specifically, a classroom. The recording system aims to automatically trace the locations of persons and the directions of their movements in a classroom, also with respect to the on- and off-seat activities. No identity of persons is kept in the recording log system, but locations of individual persons at each timestamp are obtained;hence, the spatial and temporal distribution can be studied further. In this paper, we illustrate the overview workflow of the human and seat detection as well as the log system storing human physical distancing actions. © 2022 Asia-Pacific of Signal and Information Processing Association (APSIPA).