Skip to content

Dataset · dronefreak

Road Damage Images in YOLO Format

dronefreak/RDD2022

Unofficial reconstruction of the well-known RDD2022 dataset for road defect detection.

What's inside

The dataset contains 10,000 to 100,000 annotated road damage photos categorized into 4 classes according to the CRDDC2022 taxonomy. This is a repackaged version of the multi-national RDD2022 dataset, structured into standard directory layouts for YOLO models. Annotations and metadata are presented in English under the permissive CC BY-SA 4.0 license.

What you can do with it

  • Training YOLO models for automatic pothole and road crack detection
  • Testing computer vision systems for autonomous transport and road services
Tasks
Object detection
Languages
English
Size
10K–100K rows
Downloads this month
51.5K
Likes
3

Models trained on it

How to load it

from datasets import load_dataset

ds = load_dataset("dronefreak/RDD2022")