Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Use of animal biometrics for accurate hunting evidence of wild ungulates: red deer as a model species.

Frontiers in veterinary science·2026
Same author

Non-Contrast Radiation-Free NIR Lung Imaging.

Biomedicines·2025
Same author

Phenotype Analysis in Two Families With Otopalatodigital Syndrome Spectrum Disorder Based on FLNA Gene Variants.

Clinical genetics·2025
Same author

Head poses and grimaces: Challenges for automated face identification algorithms?

Science & justice : journal of the Forensic Science Society·2024
Same author

Three-Dimensional Finger Vein Recognition: A Novel Mirror-Based Imaging Device.

Journal of imaging·2022
Same author

Zimmermann-Laband syndrome in monozygotic twins with a mild neurobehavioral phenotype lacking gingival overgrowth-A case report of a novel KCNN3 gene variant.

American journal of medical genetics. Part A·2021

Related Experiment Video

Updated: Jul 15, 2025

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

16.9K

Thermal Imaging Detection System: A Case Study for Indoor Environments.

Martin Drahanský1, Michal Charvát2, Ivo Macek3

  • 1TrendBit s.r.o., 616 00 Brno, Czech Republic.

Sensors (Basel, Switzerland)
|September 28, 2023
PubMed
Summary
This summary is machine-generated.

A new thermal imaging system uses YOLO deep learning to detect and locate people. This easily deployable, multi-camera system enhances security and automation in various environments.

Keywords:
artificial intelligencebuilding security managementinfrared imaginginfrared sensorslocalization and mappingneural networks

More Related Videos

In Situ Surface Temperature Measurement in a Conveyor Belt Furnace via Inline Infrared Thermography
07:03

In Situ Surface Temperature Measurement in a Conveyor Belt Furnace via Inline Infrared Thermography

Published on: May 30, 2020

4.5K
High-resolution Thermal Micro-imaging Using Europium Chelate Luminescent Coatings
09:01

High-resolution Thermal Micro-imaging Using Europium Chelate Luminescent Coatings

Published on: April 16, 2017

7.8K

Related Experiment Videos

Last Updated: Jul 15, 2025

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

16.9K
In Situ Surface Temperature Measurement in a Conveyor Belt Furnace via Inline Infrared Thermography
07:03

In Situ Surface Temperature Measurement in a Conveyor Belt Furnace via Inline Infrared Thermography

Published on: May 30, 2020

4.5K
High-resolution Thermal Micro-imaging Using Europium Chelate Luminescent Coatings
09:01

High-resolution Thermal Micro-imaging Using Europium Chelate Luminescent Coatings

Published on: April 16, 2017

7.8K

Area of Science:

  • Computer Vision
  • Thermal Imaging Technology
  • Artificial Intelligence

Background:

  • Increasing demand for automated people detection and localization in diverse settings like smart homes, museums, and hazardous areas.
  • Limitations of existing systems in terms of reliability, deployment ease, and multi-camera support for thermal imaging.

Purpose of the Study:

  • To develop a novel, easily deployable, and cost-effective system for automatic people detection and localization using thermal imaging.
  • To integrate state-of-the-art deep learning models with accessible hardware for real-time thermal person detection.

Main Methods:

  • Development of a control and capture library for FLIR Lepton 3.5 thermal cameras on Raspberry Pi 3B+ computers.
  • Implementation of a new person-detection technique utilizing the YOLO (You Only Look Once) deep neural network for real-time object detection.
  • Creation of a self-configuring thermal unit with a 3D-printed enclosure and automated setup using Ansible.

Main Results:

  • Successful development of a small, mountable thermal detection system capable of supporting multiple cameras.
  • Demonstrated effectiveness in people-flow analysis, validated through testing at the Czech National Museum in Prague.
  • Achieved real-time person detection and localization using thermal data, a novel application of the YOLO model.

Conclusions:

  • The presented system offers a simple, deployable solution for indoor and outdoor thermal person detection and localization.
  • The novelty lies in the effective utilization of the YOLO model for processing thermal imaging data.
  • The system serves as a valuable input for other automated systems requiring positional awareness of people.