Single Image Human Proxemics Estimation for Visual Social Distancing

Abstract

In this work, we address the problem of estimating the so-called "Social Distancing" given a single uncalibrated image in unconstrained scenarios. Our approach proposes a semi-automatic solution to approximate the homography matrix between the scene ground and image plane. With the estimated homography, we then leverage an off-the-shelf pose detector to detect body poses on the image and to reason upon their inter-personal distances using the length of their body-parts. Inter-personal distances are further locally inspected to detect possible violations of the social distancing rules. We validate our proposed method quantitatively and qualitatively against baselines on public domain datasets for which we provided groundtruth on interpersonal distances. Besides, we demonstrate the application of our method deployed in a real testing scenario where statistics on the inter-personal distances are currently used to improve the safety in a critical environment.

Reducing Viral Transmission through AI-based Crowd Monitoring and Social Distancing Analysis

“…Nawaz et al [4] also proposed a similar method and added population density analysis. [5] and [6] extend on this by using the assumption that the height of a human is approximately the same, which enables localised homographic matrices and the least squares method to perform automatic configuration and estimate inter-personal distance. Such techniques could prove valuable for an integrated crowd analysis platform, as proposed in this work.…”