Unsupervised CNN-based DIC method for 2D displacement measurement

•The paper proposes an unsupervised convolutional neural network (CNN) based DIC method for 2D displacement measurement,which eliminates the need for extensive training data annotation.•A compound loss function that combines the Mean Squared Error (MSE) and Pearson correlation coefficient is designe...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Optics and lasers in engineering Jg. 174; S. 107981
Hauptverfasser: Wang, Yixiao, Zhou, Canlin
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.03.2024
Schlagworte:
Convolutional neural network
Digital image-correlation
Loss function
Mean Absolute Error
Pearson correlation coefficient
Two-dimensional displacement measurement
Unsupervised learning
Loss function
Digital image-correlation
Convolutional neural network
Mean Absolute Error
Two-dimensional displacement measurement
Unsupervised learning
Pearson correlation coefficient
ISSN:0143-8166, 1873-0302
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•The paper proposes an unsupervised convolutional neural network (CNN) based DIC method for 2D displacement measurement,which eliminates the need for extensive training data annotation.•A compound loss function that combines the Mean Squared Error (MSE) and Pearson correlation coefficient is designed to enhance the performance and accuracy of DIC displacement measurement based on unsupervised CNN .•The accuracy achieved by the unsupervised CNN-based DIC method is comparable to that of supervised CNN-based DIC methods. Digital image correlation (DIC) is a widely used technique for non-contact measurement of deformation. However, traditional DIC methods face challenges in balancing calculation efficiency and the quantity of seed points. Deep learning approaches, particularly supervised learning methods, have shown promise in improving DIC efficiency. However, these methods require high-quality training data, which can be time-consuming to generate ground truth annotations. To address these challenges, we propose an unsupervised convolutional neural network (CNN) based DIC method for 2D displacement measurement. Our approach leverages an encoder-decoder architecture with multi-level feature extraction, a dual-path correlation block, and an attention block to extract informative features from speckle images with varying characteristics. We utilize a speckle image warp model to transform the deformed speckle image to the predicted reference speckle image based on the predicted 2D displacement map. The unsupervised training is achieved by comparing the predicted and original reference speckle images. To optimize the network's parameters, we employ a composite loss function that takes into account both the Mean Squared Error (MSE) and Pearson correlation coefficient. By using unsupervised convolutional neural network (CNN) based DIC method, we eliminate the need for extensive training data annotation, which is a time-consuming process in supervised learning DIC methods. We have conducted several experiments to demonstrate the validity and robustness of our proposed method. The results show a significant reduction in Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) compared to a method proposed by Zhao et al. This indicates that our unsupervised CNN-based DIC approach can achieve accuracy comparable to supervised CNN-based DIC methods. For implementation and evaluation, we provide PyTorch code and datasets, which will be released at the following URL :https://github.com/fead1/DICNet-corr-unsupervised-learning-.
ISSN:0143-8166
1873-0302
DOI:10.1016/j.optlaseng.2023.107981