🔬 Context-CrackNet — Pavement Crack Analyzer
A Context-Aware Framework for Precise Segmentation of Tiny Cracks in Pavement Images
Construction and Building Materials · Volume 484 · 2025 · DOI: 10.1016/j.conbuildmat.2025.141583
📤 Pavement Image
Supports JPG, PNG, TIFF — any resolution
⚙️ Model Configuration
Training Dataset
Select the hosted Context-CrackNet checkpoint to use.
0.1 0.9
✅ Default hosted model:
cracktree200/Context_CrackNet/best_attention.pthLoaded from
Blessing988/context-cracknet-weights when no override is providedArchitecture
Leave this on Context-CrackNet unless you want to try a baseline.
Use this section for baseline models or for testing a checkpoint that is not in the hosted model repo.
⏳ Upload an image and click Analyze. Default hosted model: Context_CrackNet trained on cracktree200.
📊 Crack Measurements
🔢 Crack Count
0
instances
📐 Crack Area
0
px²
📏 Crack Length
0
px
↔ Mean Width
0.0
px
↕ Max Width
0.0
px
📊 Coverage
0.00
%
Low
🖼️ Visual Analysis
Context-CrackNet · Construction and Building Materials 2025 ·
North Dakota State University ·
DOI: 10.1016/j.conbuildmat.2025.141583