**6. Summary and Final Conclusions**

In this paper, we have developed a computer vision system for automatic assessment of crack development visible on the surface of a concrete structural element during laboratory quasi-static tests. This approach combines 2D digital image correlation for monitoring the development of crack width and trained region-based convolutional neural network for automated detection and localization of multiple cracks. The intention of this work was to provide researchers and engineers with a description of easy-to-use computer vision-based system for quick assessment not only the crack width that are visible on the surface of the tested concrete element but also an automatic approach to crack detection and localization for monitoring purposes.

The computer vision system was evaluated during static tests performed in the CUT laboratory, to set up a system capable of carrying out this task. The images were captured using three DSLR cameras connected by one automatic trigger. The system showed high accuracy in assessment of the surface cracks. The system has the ability to automatic identify the cracks number and their localization. This process can be repeated for static tests of other concrete elements. Once the system was created it can be deployed for use by researchers and engineers for the concrete crack development analysis.

**Author Contributions:** Conceptualization, M.S.; methodology, M.S. and M.T.; software, M.T.; validation, M.T.; formal analysis, M.S. and M.T.; investigation, M.T. and M.S.; resources, M.T.; data curation, M.T.; writing—original draft preparation, M.S.; writing—review and editing, M.S. and M.T.; visualization, M.S. and M.T.; supervision, M.S. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research received no external funding.

**Acknowledgments:** We acknowledge support given by P. Bełda by providing results of experiments from his Master Thesis on the application of R-CNN to crack detection and localization.

**Conflicts of Interest:** The authors declare no conflict of interest.
