Next Article in Journal
Free Vibrations and Flutter Analysis of Composite Plates Reinforced with Carbon Nanotubes
Previous Article in Journal
Analysis of the Correlation of Microstructure, Instrumental Texture, and Consumer Acceptance of Shortbread Biscuits with Selected Sweeteners and Fibre
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

FTGM: Fast Transformer-Based Global Matching for Particle Image Velocimetry

1
Ocean College, Zhejiang University, Zhoushan 316034, China
2
National Key Laboratory of Intense Pulsed Radiation Situation and Effect, Northwest Institute of Nuclear Technology, Xi’an 710024, China
*
Author to whom correspondence should be addressed.
Appl. Sci. 2025, 15(3), 1138; https://doi.org/10.3390/app15031138
Submission received: 30 December 2024 / Revised: 19 January 2025 / Accepted: 21 January 2025 / Published: 23 January 2025

Abstract

The integration of deep learning with optical flow estimation in Particle Image Velocimetry (PIV) represents an emerging solution. Extensive research indicates that deep learning has potential to match or outperform state-of-the-art classical algorithms in efficiency, accuracy, and spatial resolution. However, current learning-based methods, which rely on cost volumes and convolutions for flow regression, are limited to local correlations. This limitation hinders the capture of global information. While extensive iterative refinements enhance the quality of prediction flows, they also result in a linear increase in inference time. To enhance both efficiency and accuracy, we propose a global matching method for PIV. This method directly compares feature similarities to identify correspondences between images and generate estimated flows. The underlying idea is to first extract initial features of particle image pairs, then enhance these features through a Transformer specifically designed for PIV, and perform operations for feature correlation matching, followed by global optical flow propagation and optimization. Additionally, higher-resolution features are introduced for refinement. By employing both synthetic and experimental data, including benchmark sets and data from turbulent wave channel flow experiments, we demonstrate that global matching method in PIV achieves superior efficiency and accuracy compared to existing learning-based methods.
Keywords: particle image velocimetry; transformer; optical flow; deep learning particle image velocimetry; transformer; optical flow; deep learning

Share and Cite

MDPI and ACS Style

Ding, S.; Zhao, T.; Yang, J.; Zhang, D. FTGM: Fast Transformer-Based Global Matching for Particle Image Velocimetry. Appl. Sci. 2025, 15, 1138. https://doi.org/10.3390/app15031138

AMA Style

Ding S, Zhao T, Yang J, Zhang D. FTGM: Fast Transformer-Based Global Matching for Particle Image Velocimetry. Applied Sciences. 2025; 15(3):1138. https://doi.org/10.3390/app15031138

Chicago/Turabian Style

Ding, Shuaimin, Tianqing Zhao, Jun Yang, and Dezhi Zhang. 2025. "FTGM: Fast Transformer-Based Global Matching for Particle Image Velocimetry" Applied Sciences 15, no. 3: 1138. https://doi.org/10.3390/app15031138

APA Style

Ding, S., Zhao, T., Yang, J., & Zhang, D. (2025). FTGM: Fast Transformer-Based Global Matching for Particle Image Velocimetry. Applied Sciences, 15(3), 1138. https://doi.org/10.3390/app15031138

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop