.png){kind=icon}
.png){kind=icon}
Return
From instance segmentation to physical quantification: High-resolution UAV-based dataset for façade defect assessment
.png){kind=icon}
OA
AI
DOI：10.1016/j.autcon.2026.106980.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Released a high-resolution UAV façade defect instance segmentation dataset. • Developed a UAV-oriented workflow for realistic façade defect data collection. • Benchmarked state-of-the-art segmentation models under a unified protocol. • Evaluated cross-domain transferability on public defect datasets. • Linked segmentation outputs to physical quantification and DT-based severity assessment.
Keywords:
Building inspection
Unmanned aerial vehicle
Deep learning
Instance segmentation
Defect segmentation
Defect assessment
Defect dataset
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
11.5
Papers:
6.2K
Citations:
4.2W
Organization
No organization information available