Search research 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

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 Reference-Free Lens-Flare-Aware Detector for Autonomous Driving.

Sensors (Basel, Switzerland)·2026

Same author

Large Scale in vivo Acquisition, Segmentation and 3D Reconstruction of Cortical Vasculature using <math></math> Doppler Ultrasound Imaging.

Neuroinformatics·2025

Same author

Denoising in optical coherence tomography volumes for improved 3D visualization.

Optics express·2024

Same author

Multispectral indices for real-time and non-invasive tissue ischemia monitoring using snapshot cameras.

Biomedical optics express·2024

Same author

Improving Turn Movement Count Using Cooperative Feedback.

Sensors (Basel, Switzerland)·2023

Same author

Deep Learning Tone-Mapping and Demosaicing for Automotive Vision Systems.

Sensors (Basel, Switzerland)·2023

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 21, 2025

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

Efficient Training Procedures for Multi-Spectra Demosaicing.

Ivana Shopovska¹, Ljubomir Jovanov¹, Wilfried Philips¹

¹TELIN-IPI, Ghent University-IMEC, St-Pietersnieuwstraat 41, B-9000 Gent, Belgium.

Sensors (Basel, Switzerland)

|May 21, 2020

Summary

This summary is machine-generated.

This study introduces data selection strategies for multi-spectral demosaicing using convolutional neural networks (CNNs). Optimized training data improves model accuracy and speed, even with lightweight models.

Keywords:

NIR RGB active learning data sampling deep learning demosaicing multispectral

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

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

Related Experiment Videos

Last Updated: Dec 21, 2025

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

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

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Time Multiplexing Super Resolving Technique for Imaging from a Moving Platform

Published on: February 12, 2014

Area of Science:

Computer Vision
Image Processing
Machine Learning

Background:

Simultaneous multi-spectral image acquisition uses filter arrays and single-shot capture.
Demosaicing color and near-infrared bands requires robust deep learning models.
Sufficient and varied training data is crucial for accurate convolutional neural network (CNN) training.

Purpose of the Study:

To design an efficient training procedure for multi-spectral demosaicing by discovering optimal training datasets.
To propose and evaluate data selection strategies for improving CNN-based multi-spectral demosaicing.

Main Methods:

Developed two data selection strategies: clustering-based (DSMD-C) and adaptive-based (DSMD-A).
DSMD-C aims for representative, high-variance subsets for robust model training.
DSMD-A is a self-guided approach selecting data based on current model accuracy.

Main Results:

Controlled experiments demonstrated that careful data selection benefits training speed and accuracy.
Achieved high reconstruction accuracy with lightweight models using proposed strategies.
Data selection-based multi-spectral demosaicing (DSMD) shows significant improvements.

Conclusions:

Data selection is a key factor in developing efficient and accurate multi-spectral demosaicing models.
The proposed DSMD strategies offer a viable approach for training robust CNNs.
Effective data selection enables high-performance multi-spectral imaging with reduced computational cost.