An Approach for Brick Wall Quantity Take-Off by U-Net Method Based on Deep Learning
Turkish Journal of Civil Engineering · 2024
DOI: 10.18400/tjce.1214798 ↗Kurz gefasst
Fachartikel in der Zeitschrift Turkish Journal of Civil Engineering, 2024. Verfasst von Hasan Basri BAŞAĞA und 1 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben.
Abstract (Originalsprache)
This study presents a deep learning-based method for the quantity take-off in the construction industry. In this context, the brick wall quantity calculation was performed automatically over two-dimensional (2D) pictures by the U-Net method. 280 photos were first taken in the field at different distances and angles. 1960 images were, then, obtained by augmentation to increase the training accuracy. Pixel calculation of the automatically masked area in the images was made for wall estimation. The wall area was calculated by comparing this pixel value with that of the reference brick surface area. The method was tested on four sample photos including different wall images. A parametric study was carried out to reduce the errors. In the study, it has been shown that the proposed method is suitable for brick quantity calculation. In addition, it was concluded that the photo should be taken as close as possible, and more than one brick should be taken as a reference in close-up photos to increase the accuracy.
Zitieren
APA
BAŞAĞA, H. B., & HACIEFENDİOĞLU, K. (2024). An Approach for Brick Wall Quantity Take-Off by U-Net Method Based on Deep Learning. Turkish Journal of Civil Engineering. https://doi.org/10.18400/tjce.1214798
Vancouver
BAŞAĞA HB, HACIEFENDİOĞLU K. An Approach for Brick Wall Quantity Take-Off by U-Net Method Based on Deep Learning. Turkish Journal of Civil Engineering. 2024. doi:10.18400/tjce.1214798
BibTeX
@article{BAAA2024,
author = {BAŞAĞA, Hasan Basri and HACIEFENDİOĞLU, Kemal},
title = {An Approach for Brick Wall Quantity Take-Off by U-Net Method Based on Deep Learning},
journal = {Turkish Journal of Civil Engineering},
year = {2024},
doi = {10.18400/tjce.1214798}
}
EUVIMED