moatifbutt/r2s100k

we introduce R2S100K---a large-scale dataset and benchmark for training and evaluation of road segmentation in challenging unstructured roadways.

24
/ 100
Experimental

This project helps self-driving car developers improve how autonomous vehicles 'see' and understand roads, especially in tricky, unpredictable environments. You'll input diverse images or videos of roadways, and the system outputs detailed, pixel-level maps that distinguish between safe driving surfaces and various hazards like gravel, wet spots, or vegetation. Autonomous vehicle engineers or researchers working on perception systems will find this invaluable.

Use this if you need to train or evaluate deep learning models for precise road segmentation in real-world, challenging, and unstructured driving conditions.

Not ideal if you are looking for a plug-and-play solution for vehicle control or a system for highly structured, predictable road environments.

autonomous-driving road-perception vehicle-safety machine-vision self-driving-research
No License No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

Jupyter Notebook

License

Last pushed

Jan 28, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/moatifbutt/r2s100k"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.