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

Tone Image Classification and Weighted Learning for Visible and NIR Image Fusion.

Entropy (Basel, Switzerland)·2023

Same author

Rainwater-Removal Image Conversion Learning with Training Pair Augmentation.

Entropy (Basel, Switzerland)·2023

Same author

Combined Deep Learning Techniques for Mandibular Fracture Diagnosis Assistance.

Life (Basel, Switzerland)·2022

Same author

H<sub>2</sub>O<sub>2</sub>-Responsive amphiphilic polymer with aggregation-induced emission (AIE) for DOX delivery and tumor therapy.

Bioorganic chemistry·2021

Same author

Automatic Detection of Mandibular Fractures in Panoramic Radiographs Using Deep Learning.

Diagnostics (Basel, Switzerland)·2021

Same author

Dihydropyridine-derived BODIPY probe for detecting exogenous and endogenous nitric oxide in mitochondria.

Talanta·2017

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 15, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Image Sand-Dust Removal Using Reinforced Multiscale Image Pair Training.

Dong-Min Son¹, Jun-Ru Huang¹, Sung-Hak Lee¹

¹School of Electronic and Electrical Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, Republic of Korea.

Sensors (Basel, Switzerland)

|October 16, 2025

Summary

This study introduces an advanced image enhancement technique for outdoor surveillance systems, improving visibility and color accuracy during sandstorms. The method uses deep learning and Retinex-based processing to restore clear, sharp images, outperforming existing dust removal solutions.

Keywords:

CycleGAN Retinex color preservation multi-scale image

More Related Videos

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Published on: September 29, 2019

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

Related Experiment Videos

Last Updated: Jan 15, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Published on: September 29, 2019

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training

Published on: December 6, 2024

Area of Science:

Computer Vision
Image Processing
Artificial Intelligence

Background:

Outdoor surveillance systems face challenges with low visibility and color distortion during sandstorms.
Conventional image enhancement methods struggle to restore fine details and sharp object boundaries in dusty environments.

Purpose of the Study:

To develop an image enhancement method that effectively restores image quality and preserves color consistency under sandstorm conditions.
To improve the performance of outdoor surveillance systems by mitigating the effects of sand-dust interference.

Main Methods:

A Cycle-Consistent Generative Adversarial Network (CycleGAN) was trained with unpaired images to generate synthetic data.
CycleGAN was retrained using generated and clear images for dust-interfered image transformation.
Retinex-based processing and selection of A and B chrominance channels were incorporated for enhanced clarity and color preservation.

Main Results:

The proposed method effectively restored image color and removed sand-dust interference, significantly enhancing visual quality.
Achieved a superior Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) score of 17.238 and a Local Phase Coherence-Sharpness Index (LPC-SI) of 0.973.
Outperformed established dust removal algorithms (SDIE, CVCGCBD, ROP+) and machine learning methods (Fusion, TOENet).

Conclusions:

The developed image enhancement technique significantly improves visual clarity in sandstorm conditions.
The method is highly applicable to Closed-Circuit Television (CCTV) systems, enhancing practical surveillance capabilities.
The approach offers a robust solution for maintaining image quality in adverse weather conditions.