CrackVisual-Dataset-2025: An Image Dataset for Surface Defect (Crack and Seepage) Detection in Foundation Pit Support Systems

The CrackVisual-Dataset is a specialized image collection created for training and validating machine vision-based models for detecting surface defects in foundation pit support systems. This dataset supports the research presented in the paper "Investigation into enabling machine vision and machine learning technologies for surface defect detection of pit support systems" and aims to advance research in intelligent construction, particularly for the safety monitoring of excavation engineering.