Computer vision-based concrete crack detection using U-net fully convolutional networks

Liu Zhenqing; Cao Yiwen; Wang Yize; Wang Wei

首页> 外文期刊>Automation in construction >Computer vision-based concrete crack detection using U-net fully convolutional networks

【24h】

Computer vision-based concrete crack detection using U-net fully convolutional networks

机译：使用U-net全卷积网络的基于计算机视觉的混凝土裂缝检测

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

For the first time, U-Net is adopted to detect the concrete cracks in the present study. Focal loss function is selected as the evaluation function, and the Adam algorithm is applied for optimization. The trained U-Net is able of identifying the crack locations from the input raw images under various conditions (such as illumination, messy background, width of cracks, etc.) with high effectiveness and robustness. In addition, U-Net based concrete crack detection method proposed in the present study is compared with the DCNN-based method, and U-Net is found to be more elegant than DCNN with more robustness, more effectiveness and more accurate detection. Furthermore, by examining the fundamental parameters representing the performance of the method, the present U-Net is found to reach higher accuracy with smaller training set than the previous FCNs.

机译：在本研究中，首次采用U-Net来检测混凝土裂缝。选择焦点损失函数作为评估函数，并应用Adam算法进行优化。训练有素的U-Net能够以高效率和鲁棒性从各种条件（例如照明，杂乱的背景，裂缝的宽度等）下从输入的原始图像识别裂缝位置。另外，将本研究提出的基于U-Net的混凝土裂缝检测方法与基于DCNN的方法进行了比较，发现U-Net比DCNN更为优雅，具有更强的鲁棒性，更有效和更准确的检测。此外，通过检查代表该方法性能的基本参数，发现与以前的FCN相比，本发明的U-Net在更小的训练集下可以达到更高的准确性。

著录项

来源
《Automation in construction》 |2019年第8期|129-139|共11页
作者
Liu Zhenqing; Cao Yiwen; Wang Yize; Wang Wei;
展开▼
作者单位

Huazhong Univ Sci & Technol, Sch Civil Engn & Mech, Wuhan, Hubei, Peoples R China;

Huazhong Univ Sci & Technol, Sch Civil Engn & Mech, Wuhan, Hubei, Peoples R China;

Huazhong Univ Sci & Technol, Sch Civil Engn & Mech, Wuhan, Hubei, Peoples R China;

Tokyo Inst Technol, Dept Architecture & Bldg Engn, Yokohama, Kanagawa, Japan;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Crack detection; U-net; FCN; Vision-based; Data-driven;

机译：裂缝检测;U-net;FCN;基于视觉;数据驱动;

相似文献

外文文献
中文文献
专利

1. Computer vision-based concrete crack detection using U-net fully convolutional networks [J] . Liu Zhenqing, Cao Yiwen, Wang Yize, Automation in construction . 2019,第Auga期

机译：基于计算机视觉的混凝土裂纹检测U-Net完全卷积网络
2. A vision-based active learning convolutional neural network model for concrete surface crack detection [J] . Wang Zhen, Xu Guoshan, Ding Yong, Advances in Structural Engineering . 2020,第13期

机译：基于视觉的混凝土表面裂纹检测主动学习卷积神经网络模型
3. A Crack Identification Method for Concrete Structures Using Improved U-Net Convolutional Neural Networks [J] . Wenting Qiao, Hongwei Zhang, Fei Zhu, Mathematical Problems in Engineering: Theory, Methods and Applications . 2021,第a期

机译：利用改进的U-Net卷积神经网络的混凝土结构裂缝识别方法
4. Computer vision-based Road Crack Detection Using an Improved I-UNet Convolutional Networks [C] . Leipeng Wang, Xiang-hua MA, Yinzhong Ye Chinese Control and Decision Conference . 2020

机译：使用改进的I-UNet卷积网络的基于计算机视觉的道路裂缝检测
5. Semantic Segmentation Using Modified U-Net Architecture for Crack Detection [D] . Sun, Michael. 2020

机译：使用修改的U-NET架构进行裂纹检测的语义分割
6. Vision-Based Autonomous Crack Detection of Concrete Structures Using a Fully Convolutional Encoder–Decoder Network [O] . M. M. Manjurul Islam, Jong-Myon Kim 2019

机译：使用全卷积编码器-解码器网络的基于视觉的混凝土结构自主裂缝检测
7. Vision-Based Autonomous Crack Detection of Concrete Structures Using a Fully Convolutional Encoder–Decoder Network [O] . M. M. Manjurul Islam, Jong-Myon Kim 2019

机译：基于视觉的使用全卷积编码器 - 解码器网络混凝土结构的自主裂纹检测

Computer vision-based concrete crack detection using U-net fully convolutional networks

摘要

著录项

相似文献

相关主题

期刊订阅