SpaceNet is a corpus of commercial satellite imagery and labeled training data being made available at no cost to the public to foster innovation in the development of computer vision algorithms to automatically extract information from remote sensing data.

The current SpaceNet corpus includes thousands of square kilometers of high resolution imagery collected from DigitalGlobe’s commercial satellites which includes 8-band multispectral data. 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. The currently available Areas of Interest (AOI) are Rio De Janeiro, Paris, Las Vegas, Shanghai and Khartoum. Please see the data catalog below for more information.

The satellite imagery, along with training data, is provided via a collaboration between DigitalGlobe, CosmiQ Works, and NVIDIA.

The SpaceNet dataset is being released in several Areas of Interest. All AOIs will follow a similar directory structure and data format. The imagery is GeoTIFF satellite imagery and corresponding GeoJSON building footprints. You can use the following aws-cli command to examine all files available in the dataset (details of file structure below):  

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

For more detailed information on how to access specific files within the dataset, see here.

The spacenet-dataset S3 bucket is provided as a Requester Pays bucket, see here for more information.

For a full description of the dataset, please see the overview on the SpaceNet homepage here.

Currently, cities included in the dataset are:

  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • Point of Interest (POI) Dataset- Location: Rio de Janeiro. The dataset includes POIs.
spacenet-logo2
Source
DigitalGlobe, Inc.
Category Computer Vision, Geospatial
Format GeoTIFF, GeoJSON
License Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
Storage Service Amazon S3
Location s3://spacenet-dataset in us-east-1
Update Frequency New imagery and features are added quarterly

NVIDIA demonstrates how DIGITS, their deep learning GPU training system, can be used to train two different types of convolutional neural networks for detecting buildings in the SpaceNet 3-band imagery.

See how NVIDIA is using SpaceNet data here.

Development Seed provides scripts for setting up the SpaceNet dataset for training a SegNet model via their open source package.

View the code to see how to get started using SpaceNet data here.

CosmiQ Works developed scripts to preprocess satellite imagery for consumption in machine learning frameworks and evaluation code to measure the effectiveness of object detection results.

Sample code and data can be found here.