Automatic image-based brick segmentation and crack detection of masonry walls using machine learning

Automatic image-based brick segmentation and crack detection of masonry walls using machine learning
复制标题

使用机器学习进行基于图像的砖块自动分割和砖石墙裂缝检测

DOI:
10.1016/j.autcon.2022.104389
复制
发表时间:
2022
影响因子:
10.3
通讯作者:
Loverdos D
Loverdos D
中科院分区:
工程技术1区
文献类型:
--
作者:
Loverdos D

文献摘要

参考文献

被引文献

相似文献

本文旨在通过基于图像的技术和机器学习来提高砖分割和砖墙裂缝检测的自动化程度。最初,已经开发了一个大型的手工标记图像数据集,这些图像具有不同的颜色、纹理和砖砌石墙的尺寸。然后,使用不同的深度学习网络(U-Net,DeepLabV 3+,U-Net(SM),LinkNet(SM)和FPN(SM))并评估其质量。此外,还研究了生成砌体结构的几何模型和检测到的裂缝的几何特性的评估的能力。还开发了其他指标来比较CNN输出与其他图像处理算法。结果分析表明,使用机器学习进行砖块分割比典型的图像处理应用程序提供了更好的结果。这种用于裂缝检测和砌体中砖块定位的深度学习的实施突出了新技术在记录砌体结构方面的巨大潜力。
This paper aims to improve automation in brick segmentation and crack detection of masonry walls through image-based techniques and machine learning. Initially, a large dataset of hand-labelled images of different in colour, texture, and size of brickwork masonry walls has been developed. Then, different deep learning networks (U-Net, DeepLabV3+, U-Net (SM), LinkNet (SM), and FPN (SM)) were utilised and their quality was assessed. Furthermore, the ability to generate geometric models of masonry structures and the evaluation of the geometric properties of detected cracks was also investigated. Additional metrics were also developed to compare the CNN output with other image-processing algorithms. From the analysis of results it was shown that the use of machine learning, for brick segmentation, provides better outcome than typical image-processing applications. This implementation of deep-learning for crack detection and localisation of bricks in masonry walls highlights the great potential of new technologies for documentation of masonry fabric.
一种基于图像处理的创新框架,用于裂缝砌体结构的数值建模
DOI: 10.1016/j.autcon.2021.103633
发表时间: 2021
影响因子: 10.3
作者:
Dimitrios Loverdos;V. Sarhosis;E. Adamopoulos;A. Drougkas
通讯作者: A. Drougkas
DOI: 10.1016/j.ndteint.2014.10.001
发表时间: 2015
影响因子: 4.2
作者:
F. Cluni;D. Costarelli;A. Minotti;G. Vinti
通讯作者: G. Vinti
DOI: 10.1016/j.jobe.2020.101921
发表时间: 2021-01-06
影响因子: 6.4
作者:
Hatir, Mehmet Ergun;Ince, Ismail
通讯作者: Ince, Ismail
DOI: 10.1016/j.engstruct.2020.111710
发表时间: 2021
影响因子: 5.5
作者:
N. Kassotakis;V. Sarhosis;M. Peppa;J. Mills
通讯作者: J. Mills
DOI: 10.1016/j.istruc.2021.03.111
发表时间: 2021-08
期刊: Structures
影响因子: 4.1
作者:
N. Kassotakis;V. Sarhosis
通讯作者: N. Kassotakis;V. Sarhosis