High-precision dimensional measurement of a curtain wall cross-section using image super-resolution
Jun Su Park, Hyo Seon Park
download PDFAbstract. Dimensional quality is critical to the successful installation of curtain walls, and the required dimensional tolerances are typically less than a millimeter. However, high-precision dimensional measurement of a curtain wall cross-section is practically difficult and time-consuming because the cross-sectional shapes are various and complicated, and dimensional measurement is usually performed manually in the actual field. To improve these problems, various vision-based methos are being attempted, but there have been limitations in terms of precision due to row image resolution. Therefore, this study confirmed whether image super-resolution can contribute to overcoming these limitations. To this end, an experiment on a curtain wall profile cross-section was conducted, and super-resolution generative adversarial network (SRGAN) was applied as an image super-resolution method. As a result, it was confirmed that high-precision dimensional measurement is possible from an image with enhanced resolution using SRGAN.
Keywords
High-Precision Dimensional Measurement, Curtain Wall, Super-Resolution
Published online 3/30/2023, 5 pages
Copyright © 2023 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Jun Su Park, Hyo Seon Park, High-precision dimensional measurement of a curtain wall cross-section using image super-resolution, Materials Research Proceedings, Vol. 27, pp 223-227, 2023
DOI: https://doi.org/10.21741/9781644902455-28
The article was published as article 28 of the book Structural Health Monitoring
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] Xu, D., Y. Wang, and J. Xie, Monitoring and Analysis of Building Curtain Wall Deformation Based on Optical Fiber Sensing Technology. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 2022. 46(4): p. 3081-3091. https://doi.org/10.1007/s40996-021-00735-3
[2] Eom, J. and Y. Kang, Curtain Wall Construction: Issues and Different Perspectives among Project Stakeholders. Journal of Management in Engineering, 2022. 38(5): p. 04022054. https://doi.org/10.1061/(ASCE)ME.1943-5479.0001085
[3] Zhang, P., et al., Work-health and safety-risk perceptions of construction-industry stakeholders using photograph-based Q methodology. Journal of Construction Engineering and Management, 2015. 141(5): p. 04014093. https://doi.org/10.1061/(ASCE)CO.1943-7862.0000954
[4] Liu, J. and M. Lu, Constraint programming approach to optimizing project schedules under material logistics and crew availability constraints. Journal of construction engineering and management, 2018. 144(7): p. 04018049. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001507
[5] Luo, L., et al., Supply chain management for prefabricated building projects in Hong Kong. Journal of Management in Engineering, 2020. 36(2): p. 05020001.
[6] Ledig, C., et al. Photo-realistic single image super-resolution using a generative adversarial network. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000739. https://doi.org/10.1109/CVPR.2017.19
[7] Kingma, D.P. and J. Ba, Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
