Search research articles

Related Concept Videos

Super-resolution Fluorescence Microscopy

Super-resolution Fluorescence Microscopy

Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...

You might also read

Related Articles

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

Sort by

Same author

Phase-Driven Property Modulation in BiVO<sub>4</sub> Ceramics via Multi-ion Substitution for Next-Generation Wireless Communication.

ACS applied materials & interfaces·2025

Same author

Design and Fabrication of a Patch Antenna for 5G Wireless Communications from a Low-Permittivity LiAlSi<sub>2</sub>O<sub>6</sub>-Based Ceramic.

ACS applied materials & interfaces·2024

Same author

Near-Zero Temperature Coefficient of Resonance Frequency in Rare-Earth Titanates via the Phase Transition Strategy.

ACS applied materials & interfaces·2024

Same author

Tunable Microwave Dielectric Properties in Rare-Earth Niobates via a High-Entropy Configuration Strategy To Induce Ferroelastic Phase Transition.

ACS applied materials & interfaces·2023

Same author

Phosphate and Borate-Based Composite Interface of Single-Crystal LiNi<sub>0.8</sub>Co<sub>0.1</sub>Mn<sub>0.1</sub>O<sub>2</sub> Enables Excellent Electrochemical Stability at High Operation Voltage.

Materials (Basel, Switzerland)·2023

Same author

Few-shot remote sensing image scene classification based on multiscale covariance metric network (MCMNet).

Neural networks : the official journal of the International Neural Network Society·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: Jan 13, 2026

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

Deep Relevance Hashing for Remote Sensing Image Retrieval.

Xiaojie Liu¹, Xiliang Chen^1,2, Guobin Zhu¹

¹School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China.

Sensors (Basel, Switzerland)

|October 29, 2025

Summary

This study introduces deep relevance hashing (DRH) to improve content-based remote sensing image retrieval (CBRSIR). DRH effectively handles imbalanced training data and refines retrieval results, outperforming existing deep hashing methods.

Keywords:

content-based remote sensing image retrieval (CBRSIR)deep hashing global hash learning model (GHLM)local hash re-ranking model (LHRM)

More Related Videos

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

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jan 13, 2026

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 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

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Area of Science:

Geospatial Information Science
Computer Vision
Machine Learning

Background:

Rapid growth in remote sensing data necessitates efficient image retrieval.
Deep hashing methods offer computational efficiency and accuracy for content-based remote sensing image retrieval (CBRSIR).
Existing methods struggle with imbalanced training data and distinguishing similar-yet-different images.

Purpose of the Study:

To propose a novel deep relevance hashing (DRH) method for enhanced CBRSIR.
To address the limitations of imbalanced data and inter-category confusion in deep hashing for remote sensing.
To improve the accuracy and efficiency of retrieving large-scale remote sensing images.

Main Methods:

Developed a two-stage approach: Global Hash Learning Model (GHLM) and Local Hash Re-ranking Model (LHRM).
GHLM utilizes a deep convolutional neural network with a weighted pairwise similarity loss to learn global features and generate hash codes.
LHRM employs a lightweight CNN to predict relevance scores for re-ranking retrieved images with the same Hamming distance.

Main Results:

The proposed DRH method demonstrated superior performance compared to other deep hashing approaches on three benchmark datasets.
The weighted pairwise similarity loss effectively addressed the imbalance between easy and difficult image pairs during training.
The LHRM successfully reduced confusion among images with identical Hamming distances but different categories.

Conclusions:

DRH significantly enhances the effectiveness of CBRSIR by improving feature representation and re-ranking strategies.
The method provides a robust solution for managing and retrieving large volumes of remote sensing imagery.
DRH offers a promising advancement in deep hashing techniques for geospatial data analysis.