Hands Off: A Handshake Interaction Detection and Localization Model for COVID-19 Threat Control

TL;DR

This paper introduces a real-time, non-intrusive model for detecting and localizing handshake interactions among multiple people in public spaces, aiding COVID-19 transmission control.

Contribution

It presents the first dyadic interaction localization model capable of identifying handshake interactions in multi-person scenarios in real-time.

Findings

Evaluated on over 3200 frames across two datasets

Effective in diverse real-world environments

First to localize handshake interactions in multi-person settings

Abstract

The COVID-19 outbreak has affected millions of people across the globe and is continuing to spread at a drastic scale. Out of the numerous steps taken to control the spread of the virus, social distancing has been a crucial and effective practice. However, recent reports of social distancing violations suggest the need for non-intrusive detection techniques to ensure safety in public spaces. In this paper, a real-time detection model is proposed to identify handshake interactions in a range of realistic scenarios with multiple people in the scene and also detect multiple interactions in a single frame. This is the first work that performs dyadic interaction localization in a multi-person setting. The efficacy of the proposed model was evaluated across two different datasets on more than 3200 frames, thus enabling a robust localization model in different environments. The proposed model is the first dyadic interaction localizer in a multi-person setting, which enables it to be used in public spaces to identify handshake interactions and thereby identify and mitigate COVID-19 transmission.