2D digital image correlation and region-based convolutional neural network in monitoring and evaluation of surface cracks in concrete structural elements
Authors:
- Marek Słoński,
- Marcin Tekieli
Abstract
Monitoring and evaluation of cracks visible on the surface of a concrete structural element during laboratory mechanical tests is an important part of testing procedures. Monitoring is often done by using linear-variable-differential-transformers and strain gauges. Evaluation is usually performed manually and is very time consuming. These two processes can be significantly enhanced by applying modern computer vision methods like digital image correlation and convolutional neural network. This paper shows how 2D digital image correlation (2D DIC) and region-based convolutional neural network (R-CNN) can be combined for image-based automated monitoring and assessment of surface cracks development of concrete structural elements during laboratory quasi-static tests. In the presented approach, the 2D DIC based monitoring enables estimation of deformation fields on the surface of the concrete element and measurements of cracks width. Moreover, the R-CNN model provides unmanned simultaneous detection and localization of multiple cracks in the images. The results show that the automatic monitoring and evaluation of cracks development in concrete structural elements is possible with high accuracy and reliability.
- Record ID
- CUTbfd3c3af54f040cb91801bf7fde81fbb
- Publication categories
- ;
- Author
- Journal series
- Materials, ISSN , e-ISSN 1996-1944, Biweekly
- Issue year
- 2020
- Vol
- 13
- No
- 16
- Pages
- [1-13]
- Article number
- 3527
- Other elements of collation
- fot.; rys.; schem.; wykr.; Bibliografia (na s.) - 11-13; Bibliografia (liczba pozycji) - 40; Oznaczenie streszczenia - Abstr.; Numeracja w czasopiśmie - Vol. 13, Iss. 16, Spec. Iss.
- Substantive notes
- Special Issue: Non-destructive Testing of Structures
- Keywords in English
- digital image correlation, region-based convolutional neural network, machine learning, crack monitoring, crack detection and localization
- DOI
- DOI:10.3390/ma13163527 Opening in a new tab
- URL
- https://www.mdpi.com/1996-1944/13/16/3527/htm Opening in a new tab
- Language
- eng (en) English
- License
- Score (nominal)
- 140
- Additional fields
- Indeksowana w: Web of Science, Scopus
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUTbfd3c3af54f040cb91801bf7fde81fbb/
- URN
urn:pkr-prod:CUTbfd3c3af54f040cb91801bf7fde81fbb
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.