Skip to content
All projects
Deep Learning Shipped · 2024

Concrete Crack Segmentation

U-Net semantic segmentation for infrastructure inspection

Local project
Deep Learning 2024

System architecture

  1. 01

    Dataset

    Concrete-surface imagery

  2. 02

    Model

    U-Net implemented and trained from scratch (PyTorch)

  3. 03

    Segmentation

    Pixel-level crack masks

  4. 04

    Evaluation

    Precision-oriented metrics — IoU, Dice

Pixel-level segmentation of cracks on concrete surfaces using U-Net. Trained from scratch, with particular care for precision: in infrastructure inspection, a false negative has a real cost.

What was built

  • U-Net architecture implemented and trained from scratch
  • Concrete-surface image dataset
  • Precision-oriented segmentation metrics (IoU, Dice)
  • Use case: automated infrastructure inspection

The real challenge

U-Net is still a reference for segmentation: understanding why skip connections preserve spatial detail taught me as much as the training itself.

Next project

MarketPulse AI

ask-my-portfolio · RAG