SpaceNet: Accelerating geospatial machine learning SpaceNet | SpaceNet on AWS

The SpaceNet Off-Nadir Building Detection Challenge has launched

The SpaceNet team has launched the SpaceNet Off-Nadir Building Detection Challenge on TopCoder. The Challenge will run through December 21, 2018 and offer’s $50,000 in total prizes. Read more about the dataset and challenge on the The DownlinQ and visit the Challenge page to register and compete.

This challenge focuses 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 over 665 square kilometers of downtown Atlanta and ~126,747 buildings footprints labeled from a nadir image. It is now available for download — for instructions, see the SpaceNet Off-Nadir Dataset page

Hosting

SpaceNet is a corpus of commercial satellite imagery and labeled training data to use for machine learning research. The dataset is currently hosted as an Amazon Web Services (AWS) Public Dataset.

Github Repositories

Check out our SpaceNet Utilities for some helpful tools for using geospatial data for machine learning

  1. SpaceNetUtilities
  2. Average Path Length Similarity (APLS) metric
  3. SpaceNet Building Footprint Challenge: Round 1 Solutions
  4. SpaceNet Building Footprint Challenge: Round 2 Solutions
  5. SpaceNet Road Network Extraction and Routing Challenge

Catalog

  1. Area of Interest 1 (AOI 1) - Location: Rio de Janeiro. 50cm imagery collected from DigitalGlobe’s WorldView-2 satellite. The dataset includes building footprints and 8-band multispectral data.
  2. Area of Interest 2 (AOI 2) - Location: Vegas. 30cm imagery collected from DigitalGlobe’s WorldView-3 satellite. The dataset includes building footprints and 8-band multispectral data.
  3. Area of Interest 3 (AOI 3) - Location: Paris. 30cm imagery collected from DigitalGlobe’s WorldView-3 satellite. The dataset includes building footprints and 8-band multispectral data.
  4. Area of Interest 4 (AOI 4) - Location: Shanghai. 30cm imagery collected from DigitalGlobe’s WorldView-3 satellite. The dataset includes building footprints and 8-band multispectral data.
  5. Area of Interest 5 (AOI 5) - Location: Khartoum. 30cm imagery collected from DigitalGlobe’s WorldView-3 satellite. The dataset includes building footprints and 8-band multispectral data.
  6. Area of Interest 6 (AOI 6) - Location: Atlanta 27 50cm images collected from DigitalGlobes’ WorldView-2 satellite. The dataset includes building footprints and 8-band multi-spectral data
AOI Area of Raster (Sq. Km) Building Labels (Polygons) Road Labels (LineString)
AOI_1_Rio 2,544 382,534 N/A
AOI_2_Vegas 216 151,367 3685 km
AOI_3_Paris 1,030 23,816 425 km
AOI_4_Shanghai 1,000 92,015 3537 km
AOI_5_Khartoum 765 35,503 1030 km
AOI_6_Atlanta 655 x 27 126,747 3000 km

Dependencies

The AWS Command Line Interface (CLI) must be installed with an active AWS account. Configure the AWS CLI using ‘aws configure’

aws s3 ls s3://spacenet-dataset/ --request-payer requester

Competition Updates:

For competition email updates, Sign up here

Check out CosmiQ Work’s Blog, The DownLinQ

or follow the SpaceNetUtilities Github Page