R3-DICnet: an end-to-end recursive residual refinement DIC network for larger deformation measurement
Digital image correlation (DIC) is an optical metrology method for measuring object deformation and has been widely used in many fields. Recently, the deep learning based DIC methods have achieved good performance, especially for small and complex deformation measurements. However, the existing deep...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/178543 |
| _version_ | 1826117635587178496 |
|---|---|
| author | Yang, Jiashuai Qian, Kemao Wang, Lianpo |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Yang, Jiashuai Qian, Kemao Wang, Lianpo |
| author_sort | Yang, Jiashuai |
| collection | NTU |
| description | Digital image correlation (DIC) is an optical metrology method for measuring object deformation and has been widely used in many fields. Recently, the deep learning based DIC methods have achieved good performance, especially for small and complex deformation measurements. However, the existing deep learning based DIC methods with limited measurement range cannot satisfy the needs of real-world scenarios. To tackle this problem, a recursive iterative residual refinement DIC network (R3-DICnet) is proposed in this paper, which mimics the idea of the traditional method of two-step method, where initial value estimation is performed on deep features and then iterative refinement is performed on shallow features based on the initial value, so that both small and large deformations can be accurately measured. R3-DICnet not only has high accuracy and efficiency, but also strong generalization ability. Synthetic image experiments show that the proposed R3-DICnet is suitable for both small and large deformation measurements, and it has absolute advantages in complex deformation measurement. The accuracy and generalization ability of the R3-DICnet for practical measurement experiments were also verified by uniaxial tensile and wedge splitting tests. |
| first_indexed | 2024-10-01T04:30:33Z |
| format | Journal Article |
| id | ntu-10356/178543 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:30:33Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1785432024-06-28T15:35:48Z R3-DICnet: an end-to-end recursive residual refinement DIC network for larger deformation measurement Yang, Jiashuai Qian, Kemao Wang, Lianpo School of Computer Science and Engineering Computer and Information Science Complex deformation Digital image correlations Digital image correlation (DIC) is an optical metrology method for measuring object deformation and has been widely used in many fields. Recently, the deep learning based DIC methods have achieved good performance, especially for small and complex deformation measurements. However, the existing deep learning based DIC methods with limited measurement range cannot satisfy the needs of real-world scenarios. To tackle this problem, a recursive iterative residual refinement DIC network (R3-DICnet) is proposed in this paper, which mimics the idea of the traditional method of two-step method, where initial value estimation is performed on deep features and then iterative refinement is performed on shallow features based on the initial value, so that both small and large deformations can be accurately measured. R3-DICnet not only has high accuracy and efficiency, but also strong generalization ability. Synthetic image experiments show that the proposed R3-DICnet is suitable for both small and large deformation measurements, and it has absolute advantages in complex deformation measurement. The accuracy and generalization ability of the R3-DICnet for practical measurement experiments were also verified by uniaxial tensile and wedge splitting tests. Published version Guangdong Basic and Applied Basic Research Foundation (2022A1515110036); National Natural Science Foundation of China (12302245); Natural Science Basic Research Program of Shaanxi Province (2023-JC-QN-0026); Shuangchuang Program of Jiangsu Province (JSSCBS20220943). 2024-06-25T08:09:31Z 2024-06-25T08:09:31Z 2024 Journal Article Yang, J., Qian, K. & Wang, L. (2024). R3-DICnet: an end-to-end recursive residual refinement DIC network for larger deformation measurement. Optics Express, 32(1), 907-921. https://dx.doi.org/10.1364/OE.505655 1094-4087 https://hdl.handle.net/10356/178543 10.1364/OE.505655 38175112 2-s2.0-85181080820 1 32 907 921 en Optics Express © 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement. application/pdf |
| spellingShingle | Computer and Information Science Complex deformation Digital image correlations Yang, Jiashuai Qian, Kemao Wang, Lianpo R3-DICnet: an end-to-end recursive residual refinement DIC network for larger deformation measurement |
| title | R3-DICnet: an end-to-end recursive residual refinement DIC network for larger deformation measurement |
| title_full | R3-DICnet: an end-to-end recursive residual refinement DIC network for larger deformation measurement |
| title_fullStr | R3-DICnet: an end-to-end recursive residual refinement DIC network for larger deformation measurement |
| title_full_unstemmed | R3-DICnet: an end-to-end recursive residual refinement DIC network for larger deformation measurement |
| title_short | R3-DICnet: an end-to-end recursive residual refinement DIC network for larger deformation measurement |
| title_sort | r3 dicnet an end to end recursive residual refinement dic network for larger deformation measurement |
| topic | Computer and Information Science Complex deformation Digital image correlations |
| url | https://hdl.handle.net/10356/178543 |
| work_keys_str_mv | AT yangjiashuai r3dicnetanendtoendrecursiveresidualrefinementdicnetworkforlargerdeformationmeasurement AT qiankemao r3dicnetanendtoendrecursiveresidualrefinementdicnetworkforlargerdeformationmeasurement AT wanglianpo r3dicnetanendtoendrecursiveresidualrefinementdicnetworkforlargerdeformationmeasurement |