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 Videos

Cross-Spectral Local Descriptors via Quadruplet Network.

Cristhian A Aguilera1,2, Angel D Sappa3,4, Cristhian Aguilera5

  • 1Computer Vision Center, Edifici O, Campus UAB, Bellaterra 08193, Barcelona, Spain. caguilera@cvc.uab.es.

Sensors (Basel, Switzerland)
|April 20, 2017
PubMed
Summary

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

Correction: A comprehensive analysis of YOLO architectures for tomato leaf disease identification.

Scientific reports·2025
Same author

A comprehensive analysis of YOLO architectures for tomato leaf disease identification.

Scientific reports·2025
Same author

Leveraging U-Net and selective feature extraction for land cover classification using remote sensing imagery.

Scientific reports·2025
Same author

Robotics Education in STEM Units: Breaking Down Barriers in Rural Multigrade Schools.

Sensors (Basel, Switzerland)·2023
Same author

A Novel Domain Transfer-Based Approach for Unsupervised Thermal Image Super-Resolution.

Sensors (Basel, Switzerland)·2022
Same author

SSD vs. YOLO for Detection of Outdoor Urban Advertising Panels under Multiple Variabilities.

Sensors (Basel, Switzerland)·2020
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
This summary is machine-generated.

This study introduces Q-Net, a novel CNN architecture for cross-spectral image matching. Q-Net effectively learns local feature descriptors, improving state-of-the-art performance on VIS-NIR datasets.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Remote Sensing

Background:

  • Cross-spectral image matching is crucial for tasks like surveillance and remote sensing.
  • Existing methods often struggle with the domain shift between different spectral bands.
  • Triplet networks show promise but require adaptation for cross-spectral challenges.

Purpose of the Study:

  • To develop a novel Convolutional Neural Network (CNN) architecture, Q-Net, for learning robust local feature descriptors.
  • To enable effective image patch matching across different spectral bands (e.g., visible and near-infrared).
  • To improve upon the state-of-the-art in cross-spectral matching performance.

Main Methods:

  • A quadruplet network architecture (Q-Net) is proposed, trained on matched and non-matching cross-spectral image pairs.
Keywords:
CNNcross-spectraldescriptorinfrared

Related Experiment Videos

  • Image patches are mapped to a common Euclidean space, invariant to the input spectral band.
  • The approach adapts successful triplet network concepts for cross-spectral scenarios, addressing unique non-matching pair challenges.

    • Main Results:

    • Q-Net significantly improves the state-of-the-art performance on a public cross-spectral VIS-NIR dataset.
    • The method demonstrates effectiveness in learning local feature descriptors for cross-spectral matching.
    • The technique achieves comparable performance to triplet networks in mono-spectral settings with reduced training data.

    Conclusions:

    • The proposed Q-Net architecture offers a powerful solution for cross-spectral image patch matching.
    • Q-Net provides improved accuracy and efficiency compared to existing methods.
    • The adaptability of Q-Net to mono-spectral tasks highlights its versatility.