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

A Unified Complex-Fresnel Model for Physically Based Long-Wave Infrared Imaging and Simulation.

Journal of imaging·2026

Same author

On the Measurement of Laser Lines in 3D Space with Uncertainty Estimation.

Sensors (Basel, Switzerland)·2025

Same author

A dataset of drone-captured, segmented images for oil spill detection in port environments.

Scientific data·2024

Same author

Exploring the Use of Cold Atmospheric Plasma for Sound and Vibration Generation.

Sensors (Basel, Switzerland)·2024

Same author

Single-organoid analysis reveals clinically relevant treatment-resistant and invasive subclones in pancreatic cancer.

NPJ precision oncology·2023

Same author

Seaweed Growth Monitoring with a Low-Cost Vision-Based System.

Sensors (Basel, Switzerland)·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

Search research articles

Related Experiment Video

Updated: Sep 13, 2025

Author Spotlight: Innovative Ice Cream Melting Behavior Analysis Through a Computer Vision System

Author Spotlight: Innovative Ice Cream Melting Behavior Analysis Through a Computer Vision System

Published on: October 4, 2024

Surface Ice Detection Using Hyperspectral Imaging and Machine Learning.

Steve Vanlanduit¹, Arnaud De Vooght¹, Thomas De Kerf¹

¹InViLab Research Group, Department of Electromechanical Engineering, Faculty of Applied Engineering, University of Antwerp, Groenenborgerlaan 171, 2020 Antwerpen, Belgium.

Sensors (Basel, Switzerland)

|July 30, 2025

Summary

This summary is machine-generated.

Hyperspectral imaging and machine learning effectively detect and classify ice on surfaces. This technology shows promise for monitoring ice on critical infrastructure like wind turbines, enhancing safety and performance.

Keywords:

hyperspectral imaging ice detection machine learning random forest support vector machine (SVM)wind turbine monitoring

More Related Videos

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

Related Experiment Videos

Last Updated: Sep 13, 2025

Author Spotlight: Innovative Ice Cream Melting Behavior Analysis Through a Computer Vision System

Author Spotlight: Innovative Ice Cream Melting Behavior Analysis Through a Computer Vision System

Published on: October 4, 2024

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Excitation-Scanning Hyperspectral Imaging Microscopy to Efficiently Discriminate Fluorescence Signals

Published on: August 22, 2019

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

Area of Science:

Materials Science
Remote Sensing
Artificial Intelligence

Background:

Ice accumulation on critical infrastructure, such as wind turbine blades, significantly degrades performance and poses safety risks.
Effective monitoring of ice formation is crucial for preventing failures and ensuring operational integrity.

Purpose of the Study:

To investigate the efficacy of hyperspectral imaging (HSI) combined with machine learning (ML) for detecting and classifying surface ice.
To evaluate the generalizability of ML models across different surface coatings and ice types.
To assess the impact of spectral band selection on classification performance.

Main Methods:

Acquisition of hyperspectral reflectance data using a push-broom HSI system under controlled laboratory conditions.
Generation of glaze and rime ice using a thermoelectric cooling setup on coated and uncoated surfaces.
Training and evaluation of Support Vector Machine (SVM) and Random Forest (RF) classifiers on spectral data.

Main Results:

Both SVM and RF models demonstrated high classification accuracy for surface ice detection.
Model performance decreased on black-coated surfaces due to higher light absorbance.
Distinguishing between glaze and rime ice was achieved using a multiclass RF approach.
Model performance was sensitive to spectral band selection, with SVM optimal in reduced bands and RF in full spectral range.

Conclusions:

HSI coupled with ML offers a robust solution for real-time surface ice monitoring in safety-critical applications.
The choice of ML model and spectral range impacts ice classification accuracy, particularly on varied surfaces.
This approach provides valuable data for developing targeted ice mitigation strategies for infrastructure.