mapbox/robosat

Health v2 · maintenance only

Adoption not part of the score

2064 stars · 385 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

RoboSat is an end-to-end Python pipeline for semantic segmentation and feature extraction from aerial and satellite imagery, identifying features like buildings, roads, parking lots, and water. It provides CLI tools covering the full workflow from data preparation and training to prediction and GeoJSON polygon export.

Use cases

• extract building footprints from satellite imagery
• segment roads from aerial imagery
• train a segmentation model on drone imagery
• convert satellite imagery masks to GeoJSON polygons
• detect water or parking lots in aerial photos
• generate OpenStreetMap features from imagery

When to choose

• you need an end-to-end pipeline for extracting features like buildings or roads from aerial or satellite imagery
• you want to train custom semantic segmentation models on geospatial raster data
• you are contributing to OpenStreetMap with imagery-derived features

When to avoid

• you need actively maintained software - Mapbox no longer maintains RoboSat
• you need general-purpose image segmentation outside aerial/satellite imagery
• you want a modern deep-learning framework integration with recent model architectures

Facets

library · maturity abandoned

machine-learning computer-vision image-processing cli machine-learning computer-vision python cli semantic-segmentation satellite-imagery aerial-imagery openstreetmap feature-extraction deep-learning geospatial maps linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="mapbox/robosat")