Search research articles

Search research articles

Related Experiment Video

Updated: Aug 20, 2025

Experimental Assessment of Mouse Sociability Using an Automated Image Processing Approach

Experimental Assessment of Mouse Sociability Using an Automated Image Processing Approach

Published on: May 15, 2016

Automatic social distance estimation for photographic studies: Performance evaluation, test benchmark, and algorithm.

Mert Seker¹, Anssi Männistö², Alexandros Iosifidis³

¹Unit of Computing Sciences, Tampere University, Tampere, Finland.

Machine Learning with Applications

|November 21, 2022

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Sleep Stage Specificity to Window Length Variations: A Decision Fusion Strategy for Enhanced Scoring.

IEEE journal of biomedical and health informatics·2026

Same author

Impact of labelling inaccuracy and image noise on tooth segmentation in panoramic radiographs using federated, centralized, and local learning.

Dento maxillo facial radiology·2026

Same author

Continual low-rank scaled dot-product attention.

Neural networks : the official journal of the International Neural Network Society·2025

Same author

A multimodal stress detection dataset with facial expressions and physiological signals.

Scientific data·2025

Same author

Manifold Gaussian Variational Bayes on the Precision Matrix.

Neural computation·2024

Same author

A synthetic data set to benchmark anti-money laundering methods.

Scientific data·2023

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

This study introduces a new dataset and benchmark for analyzing social distancing in photos, crucial for understanding human behavior changes post-COVID-19. The developed method accurately estimates social distances in everyday image collections.

Area of Science:

Computer Vision
Human-Computer Interaction
Social Sciences

Background:

Social distancing measures impact non-verbal communication and human behavior, necessitating proxemics studies.
Analyzing large photo collections for social distance is challenging due to varied imaging setups and lack of suitable benchmarks.
Existing safety-focused methods are not applicable for subtle social distance analysis in general image datasets.

Purpose of the Study:

To create a benchmark dataset with measured social distances for algorithm development.
To propose a standardized performance evaluation protocol for social distance estimation algorithms.
To develop an automatic social distance estimation method for general photo collections.

Main Methods:

A hybrid approach combining deep learning (object detection, pose estimation) and projective geometry.

Keywords:

Human pose estimation Performance evaluation Person detection Proxemics Social distance estimation Test benchmark

More Related Videos

Methods to Test Visual Attention Online

Methods to Test Visual Attention Online

Published on: February 19, 2015

Video Movement Analysis Using Smartphones ViMAS: A Pilot Study

Video Movement Analysis Using Smartphones ViMAS: A Pilot Study

Published on: March 14, 2017

Related Experiment Videos

Last Updated: Aug 20, 2025

Experimental Assessment of Mouse Sociability Using an Automated Image Processing Approach

Experimental Assessment of Mouse Sociability Using an Automated Image Processing Approach

Published on: May 15, 2016

Methods to Test Visual Attention Online

Methods to Test Visual Attention Online

Published on: February 19, 2015

Video Movement Analysis Using Smartphones ViMAS: A Pilot Study

Video Movement Analysis Using Smartphones ViMAS: A Pilot Study

Published on: March 14, 2017

Utilizes uncalibrated single images with known focal length and sensor size.

Dataset includes measured pair-wise social distances under diverse camera conditions.

Main Results:

Achieved a 91% human detection rate on the benchmark.
Reported an average relative distance estimation error of 38.24% among detected individuals.
Demonstrated encouraging performance on the proposed benchmark.

Conclusions:

The developed dataset and benchmark facilitate research in proxemics and social behavior analysis.
The proposed automatic estimation method shows promise for analyzing social distances in real-world image collections.
This work addresses the need for robust algorithms and evaluation protocols in social distance studies.