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

Force Classification01:22

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...

You might also read

Related Articles

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

Sort by
Same author

Breast Cancer: Model Reconstruction and Image Registration From Segmented Deformed Image Using Visual and Force Based Analysis.

IEEE transactions on medical imaging·2019
See all related articles

Related Experiment Video

Updated: Jun 10, 2026

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

A novel thermal image based cold object detection and classification using machine learning algorithms.

Siva Rajesh Chiluveru1, Mogali Tarun1, Potla Sai Lakshmi Chandana1

  • 1Computer Science Engineering, SRM University-AP, Mangalagiri, Andhra Pradesh, 522240, India.

Scientific Reports
|June 8, 2026
PubMed
Summary

This study introduces a machine learning framework for cold object detection and classification using thermal imaging. The Random Forest model achieved 99.35% accuracy, offering an effective solution for identifying low-temperature objects.

Keywords:
Cold object detection and classificationMachine learningRandom forest and XGBoostThermal imaging

More Related Videos

A Computer Vision System for the Assessment of Ice Cream Melting Behavior
08:02

A Computer Vision System for the Assessment of Ice Cream Melting Behavior

Published on: October 4, 2024

Thermal Imaging to Study Stress Non-invasively in Unrestrained Birds
10:07

Thermal Imaging to Study Stress Non-invasively in Unrestrained Birds

Published on: November 6, 2015

Related Experiment Videos

Last Updated: Jun 10, 2026

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

A Computer Vision System for the Assessment of Ice Cream Melting Behavior
08:02

A Computer Vision System for the Assessment of Ice Cream Melting Behavior

Published on: October 4, 2024

Thermal Imaging to Study Stress Non-invasively in Unrestrained Birds
10:07

Thermal Imaging to Study Stress Non-invasively in Unrestrained Birds

Published on: November 6, 2015

Area of Science:

  • Thermal Imaging Analysis
  • Machine Learning Applications
  • Object Recognition

Background:

  • Conventional visible-light imaging struggles with cold object classification due to lack of temperature data.
  • Existing research on thermal imaging for cold object detection is limited, indicating a research gap.
  • Non-contact thermal analysis offers a complementary approach to heat-focused techniques for monitoring cooling behavior and fault detection.

Purpose of the Study:

  • To develop and evaluate a machine learning framework for effective, cost-efficient, and fast cold object detection and classification using thermal images.
  • To create a dedicated dataset capturing time-dependent temperature variations for analyzing thermal behavior of cold objects.
  • To address the limitations of current methods and establish a new research direction in thermal image analysis.

Main Methods:

  • Development of a thermal image-based framework utilizing machine learning algorithms.
  • Creation of a novel dataset with time-dependent temperature variations of various cold object categories.
  • Implementation and assessment of multiple machine learning models, including Decision Tree, Random Forest, and XGBoost.

Main Results:

  • The Random Forest classifier achieved the highest classification accuracy at 99.35%.
  • The proposed framework demonstrated effectiveness in capturing temporal thermal variations for accurate cold object identification.
  • The developed dataset enabled well-ordered analysis and classification based on thermal behavior.

Conclusions:

  • Machine learning applied to thermal imaging provides a powerful tool for reliable cold object classification.
  • The Random Forest model shows significant potential for real-world applications in cold object detection.
  • This research shifts the focus in thermal image analysis towards cold object classification, opening new avenues for research.