Experimental and simulation investigation of stereo-DIC via deep learning algorithm based on initial speckle positioning technology

For deep learning-based stereo-digital image correlation technique, the initial speckle position is crucial as it influences the accuracy of the generated dataset and deformation fields. To ensure measurement accuracy, an optimized extrinsic parameter estimation algorithm is proposed in this study to determine the rotation and translation matrix of the plane in which the speckle is located between the world coordinate system and the left camera coordinate system. First, the accuracy of different extrinsic parameter estimation algorithms was studied by simulations. Subsequently, the dataset of stereo speckle images was generated using the optimized extrinsic parameters. Finally, a dual-branch convolutional neural network, named Displacement and Strain Network (DAS-Net), was established to simultaneously reconstruct the displacement and strain fields. The simulation and experimental results demonstrate that the optimized extrinsic parameters can reduce the relative displacement errors to less than 2%. Furthermore, the DAS-Net algorithm accurately measures the displacement and strain fields as well as their morphological characteristics.