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 Experiment Video

Updated: May 17, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Detecting humans using luminance saliency in thermal images.

ByoungChul Ko1, DeokYeon Kim, JaeYeal Nam

  • 1Department of Computer Engineering, Keimyung University, Shindang-Dong Dalseo-Gu, Daegu 704-701, South Korea. niceko@kmu.ac.kr

Optics Letters
|October 18, 2012
PubMed
Summary

This study presents an efficient human detection method for thermal images using center-symmetric local binary patterns (CS-LBP) and a random forest (RF) classifier. The approach focuses on head and shoulder regions for improved thermal signature analysis and detection robustness.

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

Facial Expression Recognition Based on Squeeze Vision Transformer.

Sensors (Basel, Switzerland)·2022
Same author

Model Simplification of Deep Random Forest for Real-Time Applications of Various Sensor Data.

Sensors (Basel, Switzerland)·2021
Same author

Light-Weight Student LSTM for Real-Time Wildfire Smoke Detection.

Sensors (Basel, Switzerland)·2020
Same author

Fast Depth Estimation in a Single Image Using Lightweight Efficient Neural Network.

Sensors (Basel, Switzerland)·2019
Same author

Fast human detection for intelligent monitoring using surveillance visible sensors.

Sensors (Basel, Switzerland)·2014
Same author

Image resizing using saliency strength map and seam carving for white blood cell analysis.

Biomedical engineering online·2010

Area of Science:

  • Computer Vision
  • Machine Learning
  • Thermal Imaging Analysis

Background:

  • Human detection in thermal images is challenging due to low resolution and thermal noise.
  • Conventional methods often struggle with variations in thermal signatures and environmental conditions.

Purpose of the Study:

  • To introduce an efficient and robust human detection method specifically for thermal imaging.
  • To leverage unique thermal characteristics of human body parts for improved detection accuracy.

Main Methods:

  • Utilized center-symmetric local binary pattern (CS-LBP) feature extraction.
  • Incorporated a luminance saliency map to highlight relevant thermal regions.
  • Employed a random forest (RF) classifier, an ensemble of randomized decision trees.

More Related Videos

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Related Experiment Videos

Last Updated: May 17, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

  • Focused detection on cropped head and shoulder regions for enhanced thermal contrast.

    • Main Results:

    • The proposed CS-LBP method demonstrated superior robustness compared to traditional feature descriptors.
    • The RF classifier effectively distinguished human subjects in thermal imagery.
    • The saliency map and targeted cropping improved detection performance by focusing on high-contrast areas.

    Conclusions:

    • The developed method offers an efficient and robust solution for human detection in thermal images.
    • The combination of CS-LBP, saliency maps, and RF classification shows significant promise for thermal surveillance and analysis.
    • This approach outperforms conventional techniques in thermal human detection tasks.