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 Concept Videos

Masking and Demasking Agents01:19

Masking and Demasking Agents

EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on the metal...
Deconvolution01:20

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

You might also read

Related Articles

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

Sort by
Same author

Coffee cartridge filtration: a rapid, inexpensive, and easy method to concentrate nucleic acids from pathogens and fecal biomarkers in wastewater.

Journal of applied microbiology·2026
Same author

Robust Pedestrian Detection and Intrusion Judgment in Coal Yard Hazard Areas via 3D LiDAR-Based Deep Learning.

Sensors (Basel, Switzerland)·2025
Same author

Application of CycleGAN-based low-light image enhancement algorithm in foreign object detection on belt conveyors in underground mines.

Scientific reports·2025
Same author

Photoinduced Pd-Catalyzed Intramolecular 6-<i>endo</i> Heck Reaction of Alkyl Halides.

Organic letters·2024
Same author

Tanghinigenin from seeds of Cerbera manghas L. induces apoptosis in human promyelocytic leukemia HL-60 cells.

Environmental toxicology and pharmacology·2011
Same author

The pathogenic and vaccine strains of equine infectious anemia virus differentially induce cytokine and chemokine expression and apoptosis in macrophages.

Virus research·2011

Related Experiment Video

Updated: Jul 8, 2026

Using Light Sheet Fluorescence Microscopy to Image Zebrafish Eye Development
13:01

Using Light Sheet Fluorescence Microscopy to Image Zebrafish Eye Development

Published on: April 10, 2016

33.9K

UIDF-Net: Unsupervised Image Dehazing and Fusion Utilizing GAN and Encoder-Decoder.

Anxin Zhao1, Liang Li1, Shuai Liu1

  • 1School of Communication and Information Engineering, Xi'an University of Science and Technology, Xi'an 710054, China.

Journal of Imaging
|July 26, 2024
PubMed
Summary

This study introduces a novel image dehazing network (UIDF-Net) that improves clarity and object detection in hazy conditions. The proposed method effectively removes haze, enhancing image quality for outdoor datasets.

Keywords:
haze encoderimage processingsingle image dehazingunsupervised learning

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

512

Related Experiment Videos

Last Updated: Jul 8, 2026

Using Light Sheet Fluorescence Microscopy to Image Zebrafish Eye Development
13:01

Using Light Sheet Fluorescence Microscopy to Image Zebrafish Eye Development

Published on: April 10, 2016

33.9K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

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

Published on: December 15, 2023

512

Area of Science:

  • Computer Vision
  • Image Processing
  • Artificial Intelligence

Background:

  • Haze significantly degrades image quality, reducing contrast and blurring object details.
  • Poor image quality due to haze hinders accurate object detection and reliability.
  • Existing dehazing methods often struggle with complex haze patterns and feature extraction.

Purpose of the Study:

  • To develop an advanced image dehazing and fusion network for improved visual clarity.
  • To enhance the accuracy and reliability of object detection in hazy environments.
  • To introduce novel modules for effective haze feature extraction and image fusion.

Main Methods:

  • Proposed a Unsupervised Image Dehazing and Fusion network (UIDF-Net) utilizing an encoder-decoder architecture.
  • Introduced the Image Fusion Module (MDL-IFM) for fusing dehazed image features.
  • Developed a haze encoder (Mist-Encode) to process multi-frequency image features for better haze extraction.

Main Results:

  • The UIDF-Net demonstrated superior performance in haze removal compared to existing algorithms.
  • Experimental results on outdoor datasets confirmed the effectiveness of the proposed model.
  • The fusion module and haze encoder significantly contributed to enhanced dehazing outcomes.

Conclusions:

  • The proposed UIDF-Net effectively addresses image quality degradation caused by haze.
  • The novel network architecture and modules offer a significant advancement in image dehazing technology.
  • This approach holds promise for improving various computer vision applications reliant on clear imagery.