Search research articles

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

FaceMask: A New Image Dataset for the Automated Identification of People Wearing Masks in the Wild.

Sensors (Basel, Switzerland)·2022

See all related articles

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

Search research articles

Related Experiment Video

Updated: Jul 9, 2025

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

A New Benchmark for Consumer Visual Tracking and Apparent Demographic Estimation from RGB and Thermal Images.

Iason-Ioannis Panagos¹, Angelos P Giotis¹, Sokratis Sofianopoulos²

¹Department of Computer Science and Engineering (CSE), University of Ioannina, 45110 Ioannina, Greece.

Sensors (Basel, Switzerland)

|December 9, 2023

Summary

This study introduces two new datasets for tracking and estimating consumer demographics in retail environments. The proposed framework shows promising results for accurate age and gender prediction, enhancing metadata extraction for product preferences.

Keywords:

consumer metadata consumer tracking demographic-data estimation motion prediction multi-attribute classification target detection tracklet association

More Related Videos

Thermal Imaging to Study Stress Non-invasively in Unrestrained Birds

Thermal Imaging to Study Stress Non-invasively in Unrestrained Birds

Published on: November 6, 2015

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Related Experiment Videos

Last Updated: Jul 9, 2025

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

Thermal Imaging to Study Stress Non-invasively in Unrestrained Birds

Thermal Imaging to Study Stress Non-invasively in Unrestrained Birds

Published on: November 6, 2015

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Area of Science:

Computer Vision
Machine Learning
Retail Analytics

Background:

Deep learning has advanced visual tracking and attribute estimation, but challenges remain for indoor retail consumer data.
Inadequate or inaccurate data hinders effective consumer detection, tracking, and demographic recognition in retail settings.

Purpose of the Study:

To address limitations in retail consumer data for visual tracking and demographic estimation.
To introduce novel datasets and an end-to-end framework for improved consumer analysis.

Main Methods:

Developed two datasets: 'Consumers' (145 video sequences) and 'BID' (cropped body images).
Proposed an end-to-end framework using Convolutional Neural Networks (CNNs) for object detection, Long Short-Term Memory (LSTM) networks for motion forecasting and tracklet association, and a multi-attribute classification model for demographic estimation.
Ensured compliance with personal information regulations for facial images in the 'Consumers' dataset.

Main Results:

The proposed framework achieved promising results in tracking and age/gender prediction compared to reference systems.
Demonstrated the potential for practical consumer metadata extraction, including insights into product preferences.
The 'Consumers' and 'BID' datasets provide valuable resources for computer vision tasks in retail.

Conclusions:

The developed framework and datasets offer a significant advancement in analyzing consumer behavior and demographics in retail environments.
The system shows practical potential for extracting valuable metadata related to consumer product preferences.
Further research can leverage these resources for more sophisticated retail analytics and personalized marketing strategies.