Loading...
Loading...
Contributors:
Dataset URI:
10.5281/zenodo.22801650A benchmark for rural road extraction from free 2 m CBERS-4A satellite imagery over the Anápolis/Goiás region, Brazil. It contains 40 non-overlapping 1.2 km windows, each with three independent ground-truth layers — manual photo-interpretation, OpenStreetMap, and Strava GPS tracks — plus predictions, score maps, and evaluation code. The dataset quantifies the OpenStreetMap coverage gap in rural areas and supports both zero-shot benchmarking and supervised fine-tuning. Companion to the paper "Rural Roads from Free Satellite Vision: A CBERS-4A Benchmark and the OpenStreetMap Gap" (SmartAgriVision @ SIBGRAPI 2026). See README.md for structure and licensing.
Keyword(s):
benchmark dataset; CBERS-4A; fine-tuning; map completion; OpenStreetMap.
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
No Associated Publication Data Available
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)