返回
Engineering-oriented automated crack inspection and maximum-width quantification using MSCrack
DOI:10.1016/j.measurement.2026.123242.png)
摘要
En 中文
• 提出了一种基于图像的工作流程用于自动化裂缝宽度测量。
• MSCrack仅用3.704百万参数即可实现具有竞争力的分割。
• 自动化最大裂缝宽度提取采用骨架分析和EDT。
• 在104张现场图像上的验证结果显示MAE为0.0081毫米,MRE为3.98%。
• 点级2D-3D映射支持近似的立面裂缝定位。
Keyword:
Automated crack inspection
Lightweight crack segmentation
Image-derived crack-width measurement
2D–3D crack mapping
Structural condition assessment
期刊
IF:
5.6
论文数:
2.1W
被引数:
5.4W
机构
引用论文
Crack detection and 3D visualization of crack distribution for UAV-based bridge inspection using efficient approaches基于UAV的桥梁检测中裂纹检测与裂纹分布的3D可视化高效方法
Structures
IF0
Review on computer vision-based crack detection and quantification methodologies for civil structures基于计算机视觉的土木结构裂缝检测与量化方法综述
Review on Durability Deterioration and Mitigation of Concrete Structures混凝土结构耐久性劣化及减缓措施综述
Coatings
IF0
Region of interest (ROI) extraction and crack detection for UAV-based bridge inspection using point cloud segmentation and 3D-to-2D projection基于点云分割和三维到二维投影的无人机桥梁检测感兴趣区域 (ROI) 提取和裂缝检测
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile DevicesShuffleNet: 一种用于移动设备的极其高效的卷积神经网络
Automatic detection method of tunnel lining multi-defects via an enhanced You Only Look Once network
TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformersTransunnet: 通过变形金刚的镜头重新思考医学图像分割的u-net架构设计
MEDICAL IMAGE ANALYSIS
IF11.8

