.png){kind=icon}
Return
Engineering-oriented automated crack inspection and maximum-width quantification using MSCrack
.png){kind=icon}
PRE
AI
DOI：10.1016/j.measurement.2026.123242.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• An image-based workflow is proposed for automated crack-width measurement.
• MSCrack achieves competitive segmentation with only 3.704 M parameters.
• Automated maximum crack-width extraction uses skeleton analysis and EDT..
• Validation on 104 field images yielded an MAE of 0.0081 mm and an MRE of 3.98 %.
• Point-level 2D-3D mapping supports approximate facade crack localization.
Keywords:
Automated crack inspection
Lightweight crack segmentation
Image-derived crack-width measurement
2D–3D crack mapping
Structural condition assessment
Journal
IF:
5.6
Papers:
2.1W
Citations:
5.4W
Organization
Cited Papers
Crack detection and 3D visualization of crack distribution for UAV-based bridge inspection using efficient approaches.png)
Structures
StructuresIF0
PREAI
ShareSaveShareSaveShareSaveAutomatic detection method of tunnel lining multi-defects via an enhanced You Only Look Once network
PREAI
ShareSaveTransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformersMEDICAL IMAGE ANALYSIS
OAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAIShareSave
View more