What question did this study set out to answer?

The aim is to develop an advanced method for accurately detecting and analyzing building structural cracks.

Engineering-oriented automated segmentation and quantitative analysis of building structural cracks: A multi-mechanism optimized YOLOv11-seg approach

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates improved accuracy in crack segmentation in buildings, suggesting better safety assessments.

The aim is to develop an advanced method for accurately detecting and analyzing building structural cracks.
Constructed a dedicated dataset BCrack with 450 varied crack images.
Developed an improved YOLOv11-seg model with multi-mechanism optimization.
Integrated a quantitative calculation module for measuring crack dimensions.
Achieved a mAP50 improvement from 80.2% to 83.4% in crack edge segmentation accuracy.
Measurement errors for crack length and width were controlled within 5% during field tests.

Ma et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark