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

Convolution Properties II01:17

Convolution Properties II

197
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
197
Types Of Transformers01:16

Types Of Transformers

971
Transformers can provide desired voltages to a circuit by modifying the number of turns in the secondary windings.
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
971
Deconvolution01:20

Deconvolution

159
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...
159
Convolution Properties I01:20

Convolution Properties I

147
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
147
Downsampling01:20

Downsampling

154
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
154
The Ideal Transformer01:26

The Ideal Transformer

381
In single-phase two-winding transformers, two windings are coiled around a magnetic core characterized by cross-sectional area A and magnetic permeability μ. A phasor current i1 enters the left winding while i2 exits the right winding, establishing the fundamental working of the transformer through electromagnetic principles.
Ampere's Law forms the basis of understanding the magnetic field within the transformer. It states that the integral of the magnetic field intensity's...
381

You might also read

Related Articles

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

Sort by
Same author

Long-Term Coherent Integration Algorithm for High-Speed Target Detection.

Sensors (Basel, Switzerland)·2024
Same author

Photodynamic Therapy Derived Personalized Whole Cell Tumor Vaccine Prevents Postsurgery Tumor Recurrence and Metastasis.

Small (Weinheim an der Bergstrasse, Germany)·2024
Same author

Repeated (<i>S</i>)-ketamine administration ameliorates the spatial working memory impairment in mice with chronic pain: role of the gut microbiota-brain axis.

Gut microbes·2024
Same author

Entropy-Enhanced Multi-Doping Strategy to Promote the Electrochemical Performance of Na<sub>4</sub>Fe<sub>3</sub>(PO<sub>4</sub>)<sub>2</sub>P<sub>2</sub>O<sub>7</sub>.

Small methods·2024
Same author

The Whitaker test: a predictive tool for evaluating the surgical efficacy of upper urinary tract reconstruction in patients carrying a nephrostomy tube after surgery.

International urology and nephrology·2024
Same author

Crosstalk between fibroblasts and immunocytes in fibrosis: From molecular mechanisms to clinical trials.

Clinical and translational medicine·2024

Related Experiment Video

Updated: Jun 28, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K

Contrastive Multiscale Transformer for Image Dehazing.

Jiawei Chen1, Guanghui Zhao1

  • 1School of Artificial Intelligence, Xidian University, Xi'an 710071, China.

Sensors (Basel, Switzerland)
|April 13, 2024
PubMed
Summary

This study introduces CMT-Net, a novel deep learning method for image dehazing. CMT-Net effectively restores clear images from hazy conditions by learning global features and focusing on haze-specific characteristics.

Keywords:
contrastive learning lossdeep learningimage dehazingimage processingvision transformer

More Related Videos

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects
10:16

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

12.3K
Analyzing Dendritic Morphology in Columns and Layers
08:41

Analyzing Dendritic Morphology in Columns and Layers

Published on: March 23, 2017

9.4K

Related Experiment Videos

Last Updated: Jun 28, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects
10:16

Digital Inline Holographic Microscopy DIHM of Weakly-scattering Subjects

Published on: February 8, 2014

12.3K
Analyzing Dendritic Morphology in Columns and Layers
08:41

Analyzing Dendritic Morphology in Columns and Layers

Published on: March 23, 2017

9.4K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Image Processing

Background:

  • Hazy and foggy environments degrade image quality, causing loss of detail and contrast.
  • Existing deep learning methods for image dehazing often lack specialized modules for haze characteristics and overlook features within hazy images.

Purpose of the Study:

  • To develop an innovative image dehazing method that addresses limitations of current deep neural network approaches.
  • To improve the network's ability to learn global hazy features and handle varying haze concentrations.

Main Methods:

  • Proposing Contrastive Multiscale Transformer for Image Dehazing (CMT-Net).
  • Utilizing a multiscale transformer to learn global hazy features at multiple scales.
  • Incorporating feature combination attention and a haze-aware module to prioritize hazy regions.
  • Employing a multistage contrastive learning loss with diverse samples for guided restoration.

Main Results:

  • CMT-Net demonstrates exceptional performance on established image dehazing datasets.
  • The method achieves superior visual outcomes in restoring clear images from hazy conditions.
  • Experimental findings validate the effectiveness of the proposed modules and loss function.

Conclusions:

  • CMT-Net offers a significant advancement in image dehazing technology.
  • The proposed method effectively handles diverse haze conditions and restores high-quality images.
  • This work provides a robust solution for practical image restoration in adverse environments.