BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning
This work addresses a public health monitoring challenge during pandemics like COVID-19 by providing a visual assessment tool, though it is incremental as it builds on existing detection and geometric methods.
The authors tackled the problem of assessing social distancing compliance in crowded public areas using wide field-of-view cameras by proposing BEV-Net, a multi-branch network that localizes individuals in world coordinates and identifies high-risk violations, demonstrating superior performance over baselines in experiments on complex scenes.
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 compliance assessment 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) and ground truth for metric distances is introduced, and several measures 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 high-risk regions where social distancing is violated. 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. Experiments on complex crowded scenes demonstrate the power of the approach and show superior performance over baselines derived from methods in the literature. Applications of interest for public health decision makers are finally discussed. Datasets, code and pretrained models are publicly available at GitHub.