A newer version of this model is available: Ultralytics/YOLO26

SABIQ โ€” Road Damage Detection Model

Proactive road defect detection system for Amanat Riyadh.

Model Details

  • Architecture: YOLOv26m
  • Dataset: RDD2022 (47,420 road images)
  • Classes: crack, other, pothole
  • mAP50: 0.636
  • Training: 65 epochs on Google Colab A100

Classes

ID Class Description
0 crack Longitudinal, transverse & alligator cracks
1 other Other road corruption
2 pothole Road potholes

Live API

https://rahaf2001-sabiq-api.hf.space

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Dataset used to train Rahaf2001/sabiq-road-detection