论文标题
当深度学习达到数字图像相关时
When Deep Learning Meets Digital Image Correlation
论文作者
论文摘要
卷积神经网络（CNN）构成了一类深度学习模型，这些模型已在最近使用，以解决计算机视觉中的许多问题，特别是光流估计。测量位移和应变场可以被视为此问题的特定情况。但是，看来CNN从未被用于执行此类测量。这项工作旨在实现能够从平面斑点表面的成对的参考和变形图像中检索位移和应变场的CNN，因为数字图像相关（DIC）也是如此。本文解释了如何开发称为菌株的CNN来达到此目标，以及如何详细阐述特定的地面真相数据集来训练该CNN。主要结果是应变网成功执行此类测量，并在计量性性能和计算时间方面实现竞争结果。结论是，像CLEANNET这样的CNN提供了DIC的可行替代方案，尤其是用于实时应用。
Convolutional Neural Networks (CNNs) constitute a class of Deep Learning models which have been used in the recent past to resolve many problems in computer vision, in particular optical flow estimation. Measuring displacement and strain fields can be regarded as a particular case of this problem. However, it seems that CNNs have never been used so far to perform such measurements. This work is aimed at implementing a CNN able to retrieve displacement and strain fields from pairs of reference and deformed images of a flat speckled surface, as Digital Image Correlation (DIC) does. This paper explains how a CNN called StrainNet can be developed to reach this goal, and how specific ground truth datasets are elaborated to train this CNN. The main result is that StrainNet successfully performs such measurements, and that it achieves competing results in terms of metrological performance and computing time. The conclusion is that CNNs like StrainNet offer a viable alternative to DIC, especially for real-time applications.
