Open X-Embodiment
1M+ real-robot trajectories from 20+ institutions.
São Paulo Swimming Pool Detection 8,682 chips · 26,336 bounding boxes · 97 AOIs across 96 distinct GeoSampa municipal districts (≈ 99 % of São Paulo’s land area). Splits: train 461 / val 115 (Roboflow-supervised, intentional supersets of pool-bearing and empty chips) + weak 2,709 positives-only (pool v4 @ 0.40 m/px) + highres 5,397 positives-only (pool v4 @ 0.10 m/px, native GeoSampa resolution). Resolution by split Split Chip size GSD (m/px) Ground… See the full description on the dataset page:
Source: Hugging Face Hub (cloudwalk-research/sp-swimming-pools). Metadata imported from the dataset’s Hub tags.