Posted On: Aug 25, 2016

As of today, high-resolution satellite imagery from the SpaceNet corpus is available as an AWS Public Data Set. The SpaceNet corpus includes approximately 1,900 square kilometers full-resolution 50cm imagery collected from DigitalGlobe’s WorldView-2 commercial satellite and includes 8-band multispectral data. The dataset also includes 220,594 building footprints derived from this imagery which can be used as training data for machine learning. The first Area of Interest (AOI) to released is of Rio De Janeiro, Brazil, and more AOIs will be made available in the future.

This dataset is being made public to advance the development of algorithms to automatically extract geometric features such as roads, building footprints, and points of interest using satellite imagery. Because the imagery is available on AWS, researchers and software developers can use any of our on-demand services to perform analysis and create new products without needing to worry about storage or bandwidth costs.  

To learn more about how to access and use SpaceNet data on AWS, visit: