Sub-Pixel Displacement Measurement with Swin Transformer: A Three-Level Classification Approach

In order to avoid the dependence of traditional sub-pixel displacement methods on interpolation method calculation, image gradient calculation, initial value estimation and iterative calculation, a Swin Transformer-based sub-pixel displacement measurement method (ST-SDM) is proposed, and a square da...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongxing Lin, Xiaoyan Xu, Zhixin Tie
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/5/2868
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030445325975552
author Yongxing Lin
Xiaoyan Xu
Zhixin Tie
author_facet Yongxing Lin
Xiaoyan Xu
Zhixin Tie
author_sort Yongxing Lin
collection DOAJ
description In order to avoid the dependence of traditional sub-pixel displacement methods on interpolation method calculation, image gradient calculation, initial value estimation and iterative calculation, a Swin Transformer-based sub-pixel displacement measurement method (ST-SDM) is proposed, and a square dataset expansion method is also proposed to rapidly expand the training dataset. The ST-SDM computes sub-pixel displacement values of different scales through three-level classification tasks, and solves the problem of positive and negative displacement with the rotation relative tag value method. The accuracy of the ST-SDM is verified by simulation experiments, and its robustness is verified by real rigid body experiments. The experimental results show that the ST-SDM model has higher accuracy and higher efficiency than the comparison algorithm.
format Article
id doaj-art-a0ab1a5ae694400a8cd38f29b2eef0ad
institution DOAJ
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-a0ab1a5ae694400a8cd38f29b2eef0ad2025-08-20T02:59:13ZengMDPI AGApplied Sciences2076-34172025-03-01155286810.3390/app15052868Sub-Pixel Displacement Measurement with Swin Transformer: A Three-Level Classification ApproachYongxing Lin0Xiaoyan Xu1Zhixin Tie2Keyi College, Zhejiang Sci-Tech University, Shaoxing 312369, ChinaSUPCON Technology Co., Ltd., Hangzhou 310053, ChinaKeyi College, Zhejiang Sci-Tech University, Shaoxing 312369, ChinaIn order to avoid the dependence of traditional sub-pixel displacement methods on interpolation method calculation, image gradient calculation, initial value estimation and iterative calculation, a Swin Transformer-based sub-pixel displacement measurement method (ST-SDM) is proposed, and a square dataset expansion method is also proposed to rapidly expand the training dataset. The ST-SDM computes sub-pixel displacement values of different scales through three-level classification tasks, and solves the problem of positive and negative displacement with the rotation relative tag value method. The accuracy of the ST-SDM is verified by simulation experiments, and its robustness is verified by real rigid body experiments. The experimental results show that the ST-SDM model has higher accuracy and higher efficiency than the comparison algorithm.https://www.mdpi.com/2076-3417/15/5/2868digital speckle correlation methoddigital image correlation methodsub-pixel displacement methoddeep learningsquare dataset expansion method
spellingShingle Yongxing Lin
Xiaoyan Xu
Zhixin Tie
Sub-Pixel Displacement Measurement with Swin Transformer: A Three-Level Classification Approach
Applied Sciences
digital speckle correlation method
digital image correlation method
sub-pixel displacement method
deep learning
square dataset expansion method
title Sub-Pixel Displacement Measurement with Swin Transformer: A Three-Level Classification Approach
title_full Sub-Pixel Displacement Measurement with Swin Transformer: A Three-Level Classification Approach
title_fullStr Sub-Pixel Displacement Measurement with Swin Transformer: A Three-Level Classification Approach
title_full_unstemmed Sub-Pixel Displacement Measurement with Swin Transformer: A Three-Level Classification Approach
title_short Sub-Pixel Displacement Measurement with Swin Transformer: A Three-Level Classification Approach
title_sort sub pixel displacement measurement with swin transformer a three level classification approach
topic digital speckle correlation method
digital image correlation method
sub-pixel displacement method
deep learning
square dataset expansion method
url https://www.mdpi.com/2076-3417/15/5/2868
work_keys_str_mv AT yongxinglin subpixeldisplacementmeasurementwithswintransformerathreelevelclassificationapproach
AT xiaoyanxu subpixeldisplacementmeasurementwithswintransformerathreelevelclassificationapproach
AT zhixintie subpixeldisplacementmeasurementwithswintransformerathreelevelclassificationapproach