Human localization using a single camera towards social distance monitoring during sports

Coronavirus disease 2019 (COVID-19) is still prevalent in the world. Social distancing is more important during exercise because we may not be able to wear masks to avoid breathing problems, heatstroke, etc. For supporting management of social distancing, we are developing a human localization system using a single camera especially for sports schools and gyms. We rely on a single camera because of the deployment cost. The system recognizes people from a video and estimates the human positions for supporting management of social distancing. The challenge is the error owing to pose variation during sports. In order to solve the problem, we adjust the height of the waist according to the pose of the legs. For evaluation, we collected 80 images with 5 kinds of poses. The results show that we successfully reduce the absolute position error by 23 cm on average.

In EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous 2021)