SpaceNet

Description

SpaceNet, launched in August 2016 as an open innovation project offering a repository of freely available imagery with co-registered map features. Before SpaceNet, computer vision researchers had minimal options to obtain free, precision-labeled, and high-resolution satellite imagery. Today, SpaceNet hosts datasets developed by its own team, along with data sets from projects like IARPA’s Functional Map of the World (fMoW).

Update Frequency

New imagery and features are added quarterly

License

Various (See here for more details)

Documentation

http://www.spacenet.ai/

Managed By

See all datasets managed by SpaceNet.

Contact

https://github.com/SpaceNetChallenge/utilities/issues

Usage Examples

Tutorials

• Extracting buildings and roads from AWS Open Data using Amazon SageMaker by Yunzhi Shi, Tianyu Zhang, and Xin Chen
  SageMaker
• Getting Started with SpaceNet Data by Adam Van Etten
  

Tools & Applications

• Solaris: an open source Python library for analyzing overhead imagery with machine learning by Nick Weir
  

Publications

• 2nd SpaceNet Competition Winners Code Release by David Lindenbaum
  
• Building Extraction with YOLT2 and SpaceNet Data by Adam Van Etten
  
• Introducing the SpaceNet Road Detection and Routing Challenge and Dataset by David Lindenbaum
  
• Solving SpaceNet Road Detection Challenge With Deep Learning by Jonathan Howe, May Casterline and Abel Brown
  
• SpaceNet: Winning Implementations and New Imagery Release by Todd Stavish