Accelerating Geospatial Machine Learning
SpaceNet delivers access to high-quality geospatial data for developers, researchers, and startups. Before SpaceNet, computer vision researchers had minimal options to obtain free, precision-labeled, and high-resolution satellite imagery. SpaceNet focuses on four open source key pillars: data, challenges, algorithms, and tools.
SpaceNet 4 Challenge
Off-Nadir Building Detection Challenge
Can off-nadir imagery help automate mapping? This challenge focused on the use of off-nadir imagery for building footprint extraction. The dataset includes 27 WorldView 2 Satellite images from 7 degrees to 54 degrees off-nadir, all captured within 5 minutes of each other. The dataset covers more than 665 square kilometers of downtown Atlanta and ~127,000 buildings footprints labeled from a nadir image. Visit the SpaceNet Off-Nadir Dataset page for download instructions.
Off-nadir satellite views over Atlanta ranging from 7 to 54 degrees
Algorithm Repository
Explore algorithms used to solve SpaceNet challenges. These currently include 13 open source Building footprint and Road Network extraction problems.
Collaborators
