Promise Into Practice: Application of Computer Vision in Empirical Research on Social Distancing

Wim Bernasco*, Evelien M. Hoeben, Dennis Koelma, Lasse Suonperä Liebst, Josephine Thomas, Joska Appelman, Cees G.M. Snoek, Marie Rosenkrantz Lindegaard

*Corresponding author for this work

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Social scientists increasingly use video data, but large-scale analysis of its content is often constrained by scarce manual coding resources. Upscaling may be possible with the application of automated coding procedures, which are being developed in the field of computer vision. Here, we introduce computer vision to social scientists, review the state-of-the-art in relevant subfields, and provide a working example of how computer vision can be applied in empirical sociological work. Our application involves defining a ground truth by human coders, developing an algorithm for automated coding, testing the performance of the algorithm against the ground truth, and running the algorithm on a large-scale dataset of CCTV images. The working example concerns monitoring social distancing behavior in public space over more than a year of the COVID-19 pandemic. Finally, we discuss prospects for the use of computer vision in empirical social science research and address technical and ethical challenges.

Original languageEnglish
Pages (from-to)1239-1287
JournalSociological Methods and Research
Volume52
Issue number3
DOIs
Publication statusPublished - 2023

Bibliographical note

Publisher Copyright:
© The Author(s) 2022.

Funding

The authors thank Kiki Bijleveld at the NSCR for assistance in processing and coding video data, and Maikel van Scheppingen, Makki el Jouhri and Tineke Gortworst-Michels at the Amsterdam Police Department for assistance in securing video data. he author(s) disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: ZonMW no. 10430022010017 (‘Towards evidence-based social distancing policy’).

FundersFunder number
NSCR
ZonMw10430022010017

    Keywords

    • Computer vision
    • deep learning
    • pedestrian detection
    • social distancing
    • video data analysis

    Fingerprint

    Dive into the research topics of 'Promise Into Practice: Application of Computer Vision in Empirical Research on Social Distancing'. Together they form a unique fingerprint.

    Cite this