Detecting F-formations & Roles in Crowded Social Scenes with Wearables: Combining Proxemics & Dynamics using LSTMs

TL;DR

This paper presents a method using wearable sensors and LSTMs to detect social group formations and roles in crowded scenes, achieving high accuracy by combining proxemics and dynamics data.

Contribution

It introduces a novel approach that jointly models proxemics and dynamics with wearable sensors for F-formation and role detection, outperforming previous methods.

Findings

Fusion of proxemics and dynamics yields AUC of 0.975.

Different roles require different time resolutions for detection.

Single sensor data can effectively identify social groupings.

Abstract

In this paper, we investigate the use of proxemics and dynamics for automatically identifying conversing groups, or so-called F-formations. More formally we aim to automatically identify whether wearable sensor data coming from 2 people is indicative of F-formation membership. We also explore the problem of jointly detecting membership and more descriptive information about the pair relating to the role they take in the conversation (i.e. speaker or listener). We jointly model the concepts of proxemics and dynamics using binary proximity and acceleration obtained through a single wearable sensor per person. We test our approaches on the publicly available MatchNMingle dataset which was collected during real-life mingling events. We find out that fusion of these two modalities performs significantly better than them independently, providing an AUC of 0.975 when data from 30-second windows are used. Furthermore, our investigation into roles detection shows that each role pair requires a different time resolution for accurate detection.