SpaceNet Overview – Open Datasets and Prize Challenges

Date: Tuesday, August 15, 2017

Time: 9:30 am – 11:00 am ET

FOSS4G 2017
Harborview I in the Seaport
World Trade Center

Registration for this training session is closed.

Todd Bacastow

SpaceNet lead for DigitalGlobe | Radiant

For more information, please reach us at:

David Lindenbaum

Principal Engineer, CosmiQ Works, an IQT Lab

For more information, please reach us at:

SpaceNet is an online repository of openly available satellite imagery, co-registered map data to train algorithms, and a series of public challenges designed to accelerate innovation in machine learning using geospatial data. This first-of-its-kind open innovation project for the geospatial industry is a collaboration between CosmiQ Works, DigitalGlobe and NVIDIA.

What You Will Learn:

This training session provides an introduction to SpaceNet. Registered users will learn how qualified SpaceNet participants can:
• Access over 6,584 km2 of open high-resolution imagery and more than 520,000 vectors through SpaceNet on AWS
• Utilize open source tools and algorithms available at the SpaceNet GitHub Repo
• Compete for prize money in upcoming SpaceNet Challenges by developing new algorithms for geospatial applications like automated mapping