Automatic Social Distance Estimation From Images: Performance Evaluation, Test Benchmark, and Algorithm

The COVID-19 pandemic has been ongoing since March 2020. While social distancing regulations can slow the spread of the virus, they also directly affect a basic form of non-verbal communication, and there may be longer term impacts on human behavior and culture that remain to be analyzed in proxemics studies. To obtain quantitative results for such studies, large numbers of personal and/or media photos must be analyzed. Several social distance monitoring methods have been proposed for safety purposes, but they are not directly applicable to general photo collections with large variations in the imaging setup. In such studies, the interest shifts from safety to analyzing subtle differences in social distances. Currently, there is no suitable benchmark for developing such algorithms. Collecting images with measured ground-truth pair-wise distances using different camera settings is cumbersome. Moreover, performance evaluation for these algorithms is not straightforward, and there is no widely accepted evaluation protocol. In this paper, we provide an image dataset with measured pair-wise social distances under different camera positions and settings. We suggest a performance evaluation protocol and provide a benchmark to easily evaluate such algorithms. We also propose an automatic social distance estimation method that can be applied on general photo collections. Our method builds on object detection and human pose estimation. It can be applied on uncalibrated single images with known focal length and sensor size. The results on our benchmark are encouraging with 91% human detection rate and only 38.24% average relative distance estimation error among the detected people.