BEV-Net

Social distancing, an essential public health measure to limit the spread of contagious diseases, has gained significant attention since the outbreak of the COVID-19 pandemic. In this work, the problem of visual social distancing detection in busy public areas, with wide field-of-view cameras, is considered. A dataset of crowd scenes with people annotations under a bird’s eye view (BEV) is introduced, and several metrics for the evaluation of social distance detection systems are proposed. A multi-branch network, BEV-Net, is proposed to localize individuals in world coordinates and identify clusters of people within a minimum safe distance of one another. BEV-Net combines detection of head and feet locations, camera pose estimation, a differentiable homography module to map image into BEV coordinates, and geometric reasoning to produce a BEV map of the people locations in the scene.