Identification of social relation within pedestrian dyads

Zeynep Yucel, Francesco Zanlungo, Claudio Feliciani, Adrien Gregorj, Takayuki Kanda

Research output: Contribution to journalArticle

Abstract

This study focuses on social pedestrian groups in public spaces and makes an effort to identify the type of social relation between the group members. As a first step for this identification problem, we focus on dyads (i.e. 2 people groups). Moreover, as a mutually exclusive categorization of social relations, we consider the domain-based approach of Bugental, which precisely corresponds to social relations of colleagues, couples, friends and families, and identify each dyad with one of those relations. For this purpose, we use anonymized trajectory data and derive a set of observables thereof, namely, inter-personal distance, group velocity, velocity difference and height difference. Subsequently, we use the probability density functions (pdf) of these observables as a tool to understand the nature of the relation between pedestrians. To that end, we propose different ways of using the pdfs. Namely, we introduce a probabilistic Bayesian approach and contrast it to a functional metric one and evaluate the performance of both methods with appropriate assessment measures. This study stands out as the first attempt to automatically recognize social relation between pedestrian groups. Additionally, in doing that it uses completely anonymous data and proves that social relation is still possible to recognize with a good accuracy without invading privacy. In particular, our findings indicate that significant recognition rates can be attained for certain categories and with certain methods. Specifically, we show that a very good recognition rate is achieved in distinguishing colleagues from leisure-oriented dyads (families, couples and friends), whereas the distinction between the leisure-oriented dyads results to be inherently harder, but still possible at reasonable rates, in particular if families are restricted to parent-child groups. In general, we establish that the Bayesian method outperforms the functional metric one due, probably, to the difficulty of the latter to learn observable pdfs from individual trajectories.

Original languageEnglish
Article numbere0223656
JournalPloS one
Volume14
Issue number10
DOIs
Publication statusPublished - Jan 1 2019

Fingerprint

Social Identification
trajectories
Bayes Theorem
Leisure Activities
Trajectories
Bayesian theory
Probability density function
Privacy
methodology
Pedestrians

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)
  • General

Cite this

Yucel, Z., Zanlungo, F., Feliciani, C., Gregorj, A., & Kanda, T. (2019). Identification of social relation within pedestrian dyads. PloS one, 14(10), [e0223656]. https://doi.org/10.1371/journal.pone.0223656

Identification of social relation within pedestrian dyads. / Yucel, Zeynep; Zanlungo, Francesco; Feliciani, Claudio; Gregorj, Adrien; Kanda, Takayuki.

In: PloS one, Vol. 14, No. 10, e0223656, 01.01.2019.

Research output: Contribution to journalArticle

Yucel, Z, Zanlungo, F, Feliciani, C, Gregorj, A & Kanda, T 2019, 'Identification of social relation within pedestrian dyads', PloS one, vol. 14, no. 10, e0223656. https://doi.org/10.1371/journal.pone.0223656
Yucel Z, Zanlungo F, Feliciani C, Gregorj A, Kanda T. Identification of social relation within pedestrian dyads. PloS one. 2019 Jan 1;14(10). e0223656. https://doi.org/10.1371/journal.pone.0223656
Yucel, Zeynep ; Zanlungo, Francesco ; Feliciani, Claudio ; Gregorj, Adrien ; Kanda, Takayuki. / Identification of social relation within pedestrian dyads. In: PloS one. 2019 ; Vol. 14, No. 10.
@article{aaf9dd66469945e2ab097a6b4840f96e,
title = "Identification of social relation within pedestrian dyads",
abstract = "This study focuses on social pedestrian groups in public spaces and makes an effort to identify the type of social relation between the group members. As a first step for this identification problem, we focus on dyads (i.e. 2 people groups). Moreover, as a mutually exclusive categorization of social relations, we consider the domain-based approach of Bugental, which precisely corresponds to social relations of colleagues, couples, friends and families, and identify each dyad with one of those relations. For this purpose, we use anonymized trajectory data and derive a set of observables thereof, namely, inter-personal distance, group velocity, velocity difference and height difference. Subsequently, we use the probability density functions (pdf) of these observables as a tool to understand the nature of the relation between pedestrians. To that end, we propose different ways of using the pdfs. Namely, we introduce a probabilistic Bayesian approach and contrast it to a functional metric one and evaluate the performance of both methods with appropriate assessment measures. This study stands out as the first attempt to automatically recognize social relation between pedestrian groups. Additionally, in doing that it uses completely anonymous data and proves that social relation is still possible to recognize with a good accuracy without invading privacy. In particular, our findings indicate that significant recognition rates can be attained for certain categories and with certain methods. Specifically, we show that a very good recognition rate is achieved in distinguishing colleagues from leisure-oriented dyads (families, couples and friends), whereas the distinction between the leisure-oriented dyads results to be inherently harder, but still possible at reasonable rates, in particular if families are restricted to parent-child groups. In general, we establish that the Bayesian method outperforms the functional metric one due, probably, to the difficulty of the latter to learn observable pdfs from individual trajectories.",
author = "Zeynep Yucel and Francesco Zanlungo and Claudio Feliciani and Adrien Gregorj and Takayuki Kanda",
year = "2019",
month = "1",
day = "1",
doi = "10.1371/journal.pone.0223656",
language = "English",
volume = "14",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "10",

}

TY - JOUR

T1 - Identification of social relation within pedestrian dyads

AU - Yucel, Zeynep

AU - Zanlungo, Francesco

AU - Feliciani, Claudio

AU - Gregorj, Adrien

AU - Kanda, Takayuki

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This study focuses on social pedestrian groups in public spaces and makes an effort to identify the type of social relation between the group members. As a first step for this identification problem, we focus on dyads (i.e. 2 people groups). Moreover, as a mutually exclusive categorization of social relations, we consider the domain-based approach of Bugental, which precisely corresponds to social relations of colleagues, couples, friends and families, and identify each dyad with one of those relations. For this purpose, we use anonymized trajectory data and derive a set of observables thereof, namely, inter-personal distance, group velocity, velocity difference and height difference. Subsequently, we use the probability density functions (pdf) of these observables as a tool to understand the nature of the relation between pedestrians. To that end, we propose different ways of using the pdfs. Namely, we introduce a probabilistic Bayesian approach and contrast it to a functional metric one and evaluate the performance of both methods with appropriate assessment measures. This study stands out as the first attempt to automatically recognize social relation between pedestrian groups. Additionally, in doing that it uses completely anonymous data and proves that social relation is still possible to recognize with a good accuracy without invading privacy. In particular, our findings indicate that significant recognition rates can be attained for certain categories and with certain methods. Specifically, we show that a very good recognition rate is achieved in distinguishing colleagues from leisure-oriented dyads (families, couples and friends), whereas the distinction between the leisure-oriented dyads results to be inherently harder, but still possible at reasonable rates, in particular if families are restricted to parent-child groups. In general, we establish that the Bayesian method outperforms the functional metric one due, probably, to the difficulty of the latter to learn observable pdfs from individual trajectories.

AB - This study focuses on social pedestrian groups in public spaces and makes an effort to identify the type of social relation between the group members. As a first step for this identification problem, we focus on dyads (i.e. 2 people groups). Moreover, as a mutually exclusive categorization of social relations, we consider the domain-based approach of Bugental, which precisely corresponds to social relations of colleagues, couples, friends and families, and identify each dyad with one of those relations. For this purpose, we use anonymized trajectory data and derive a set of observables thereof, namely, inter-personal distance, group velocity, velocity difference and height difference. Subsequently, we use the probability density functions (pdf) of these observables as a tool to understand the nature of the relation between pedestrians. To that end, we propose different ways of using the pdfs. Namely, we introduce a probabilistic Bayesian approach and contrast it to a functional metric one and evaluate the performance of both methods with appropriate assessment measures. This study stands out as the first attempt to automatically recognize social relation between pedestrian groups. Additionally, in doing that it uses completely anonymous data and proves that social relation is still possible to recognize with a good accuracy without invading privacy. In particular, our findings indicate that significant recognition rates can be attained for certain categories and with certain methods. Specifically, we show that a very good recognition rate is achieved in distinguishing colleagues from leisure-oriented dyads (families, couples and friends), whereas the distinction between the leisure-oriented dyads results to be inherently harder, but still possible at reasonable rates, in particular if families are restricted to parent-child groups. In general, we establish that the Bayesian method outperforms the functional metric one due, probably, to the difficulty of the latter to learn observable pdfs from individual trajectories.

UR - http://www.scopus.com/inward/record.url?scp=85073533338&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073533338&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0223656

DO - 10.1371/journal.pone.0223656

M3 - Article

C2 - 31622383

AN - SCOPUS:85073533338

VL - 14

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 10

M1 - e0223656

ER -