ECI-Net: A modular and lightweight Deep DIC network for real-time robust 2D displacement measurement

被引:0
作者
Wang, Zitong [1 ]
Zhu, Pan [1 ]
Guan, Jiaxi [2 ]
Liu, Lu [1 ]
Zhou, Xinglin [1 ]
机构
[1] Wuhan Univ Sci & Technol, Sch Machinery & Automat, Wuhan 430081, Peoples R China
[2] Hubei Institue Measurement & Testing Technol, Wuhan 430223, Peoples R China
关键词
Digital image correlation; Displacement field estimation; Convolutional neural network; DIGITAL IMAGE CORRELATION;
D O I
10.1016/j.optlastec.2024.112376
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Deep learning-based Digital Image Correlation (Deep DIC) is considered a potential method to overcoming the issues of Digital Image Correlation (DIC), such as accuracy, and efficiency. However, the current Deep DICs may struggle to accommodate various types of deformations, which affects their stability. To address the issue, referring to the previous Deep DIC architecture and traditional DIC, we propose a lightweight architecture called ECI-Net, which includes three modules: extractor, correlator, and integrator. To enable the network to generalize across multiple displacement modes within a +/- 10 pixel range, an artificial speckle dataset is generated, which helps the network better adapt to small deformation scenarios encountered in real-world applications. The proposed modules' effectiveness is demonstrated through ablation experiments. The constancy of ECI-Net is proved through a test set that included various displacement modes various displacement modes and ranges. Meanwhile, ECI-Net is also validated as a stable Deep DIC in real experiments.
引用
收藏
页数:15
相关论文
共 46 条
[1]  
Alhashim I, 2018, HIGH QUALITY MONOCUL
[2]  
[Anonymous], 2014, Comput. Sci.
[3]  
Ba J., 2014, 3 INT C LEARN REPR I
[4]   A lightweight convolutional neural network as an alternative to DIC to measure in-plane displacement fields [J].
Boukhtache, S. ;
Abdelouahab, K. ;
Bahou, A. ;
Berry, F. ;
Blaysat, B. ;
Grediac, M. ;
Sur, F. .
OPTICS AND LASERS IN ENGINEERING, 2023, 161
[5]   When Deep Learning Meets Digital Image Correlation [J].
Boukhtache, S. ;
Abdelouahab, K. ;
Berry, F. ;
Blaysat, B. ;
Grediac, M. ;
Sur, F. .
OPTICS AND LASERS IN ENGINEERING, 2021, 136
[6]   DIGITAL IMAGE CORRELATION USING NEWTON-RAPHSON METHOD OF PARTIAL-DIFFERENTIAL CORRECTION [J].
BRUCK, HA ;
MCNEILL, SR ;
SUTTON, MA ;
PETERS, WH .
EXPERIMENTAL MECHANICS, 1989, 29 (03) :261-267
[7]   Fast and large-converge-radius inverse compositional Levenberg-Marquardt algorithm for digital image correlation: principle, validation, and open-source toolbox [J].
Chen, Bin ;
Jungstedt, Erik .
OPTICS AND LASERS IN ENGINEERING, 2022, 151
[8]   Extended digital image correlation method for analysis of discrete discontinuity [J].
Deb, Debasis ;
Bhattacharjee, Sudipta .
OPTICS AND LASERS IN ENGINEERING, 2015, 74 :59-66
[9]   FlowNet: Learning Optical Flow with Convolutional Networks [J].
Dosovitskiy, Alexey ;
Fischer, Philipp ;
Ilg, Eddy ;
Haeusser, Philip ;
Hazirbas, Caner ;
Golkov, Vladimir ;
van der Smagt, Patrick ;
Cremers, Daniel ;
Brox, Thomas .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :2758-2766
[10]   A morphing-based scheme for large deformation analysis with stereo-DIC [J].
Genovese, Katia ;
Sorgente, Donato .
OPTICS AND LASERS IN ENGINEERING, 2018, 104 :159-172