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

You might also read

Related Articles

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

Sort by
Same author

NUAK1 silencing enhances radiotherapy-induced ferroptosis in locally advanced rectal cancer by impairing Nrf2-driven transcription of GPX4.

Cellular oncology (Dordrecht, Netherlands)·2026
Same author

LL-37-derived peptide shows promising antimicrobial potential against multidrug-resistance pathogens.

European journal of medicinal chemistry·2026
Same author

Molecular defense strategy of volatile organic compound-emitting plants (order Piperales) against herbivorous mammals.

Communications biology·2025
Same author

Understanding animal temperature sensation: from molecular thermosensors to physiological impacts.

Science China. Life sciences·2025
Same author

Personalized Neoantigen Vaccine plus Regorafenib Increases Rgs2⁺CD8⁺ T Cells Infiltration and Reprograms the Tumor Microenvironment in Microsatellite Stable Colorectal Cancer Liver Metastases.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025
Same author

Quantitative proteomics analysis of radiation-induced rectal injury in rectal cancer patients undergoing radiotherapy.

Journal of proteomics·2025

Related Experiment Video

Updated: Jul 16, 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

1.9K

Displacement extraction of background-oriented schlieren images using Swin Transformer.

Huajun Cai, Yang Song, Yunjing Ji

    Journal of the Optical Society of America. A, Optics, Image Science, and Vision
    |September 14, 2023
    PubMed
    Summary
    This summary is machine-generated.

    A new deep neural network accurately extracts displacement from background-oriented schlieren (BOS) images. This AI approach surpasses traditional cross-correlation and optical flow methods for improved flow field reconstruction.

    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
    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
    13:44

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

    Published on: August 30, 2013

    42.9K

    Related Experiment Videos

    Last Updated: Jul 16, 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

    1.9K
    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
    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
    13:44

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

    Published on: August 30, 2013

    42.9K

    Area of Science:

    • Fluid Dynamics
    • Optical Measurement Techniques
    • Image Processing

    Background:

    • Accurate displacement extraction is crucial for background-oriented schlieren (BOS) reconstruction.
    • Conventional methods like cross-correlation (CC) and optical flow (OF) have limitations in BOS displacement estimation.
    • Existing methods often require manual parameter tuning, impacting efficiency and accuracy.

    Purpose of the Study:

    • To develop an advanced deep learning model for end-to-end displacement extraction in BOS.
    • To overcome the limitations of traditional CC and OF methods in BOS applications.
    • To provide a robust and automated solution for BOS displacement estimation.

    Main Methods:

    • An end-to-end deep neural network architecture was designed, utilizing a Swin Transformer for enhanced long-range correlation capture.
    • A synthetic dataset was generated using computational fluid dynamics (CFD) simulations for model training.
    • The trained network directly estimates BOS displacement from image pairs without requiring additional parameters.

    Main Results:

    • The proposed Swin Transformer-based network demonstrated stable performance on both synthetic and real experimental BOS images.
    • Experimental validation confirmed the superiority of the deep learning approach over conventional CC and OF methods.
    • The network outperformed classic convolutional neural networks specifically designed for optical flow tasks.

    Conclusions:

    • The developed deep neural network offers a highly effective and stable method for BOS displacement extraction.
    • This AI-driven approach significantly improves upon traditional techniques, paving the way for more accurate flow field analysis.
    • The method's ability to perform without additional parameters simplifies the BOS reconstruction process.