SpaceNet 7

building footprints planetscope segmentation

Description

The SpaceNet 7 Multi-Temporal Urban Development Challenge aims to help address this deficit and develop novel computer vision methods for non-video time series data.

In this challenge, participants will identify and track buildings in satellite imagery time series collected over rapidly urbanizing areas.

The competition centers around a new open source dataset of Planet satellite imagery mosaics, which includes 24 images (one per month) covering ~100 unique geographies.

Documentation

https://spacenet.ai/sn7-challenge/

Citation

SpaceNet on Amazon Web Services (AWS). “Datasets.” The SpaceNet Catalog. Last modified April 30, 2018. Accessed on [Insert Date]. https://spacenetchallenge.github.io/datasets/datasetHomePage.html.

Created By

Contact

Usage Examples

Tools & Applications
Publications

STAC Collections

  • Description
    SpaceNet 7 Training Labels
    Resource type
    Labels
    Collection ID
    sn7_train_labels
    License
    CC-BY-SA-4.0
  • Description
    SpaceNet 7 Training Source Imagery
    Resource type
    Source Imagery
    Collection ID
    sn7_train_source
    License
    CC-BY-SA-4.0
  • Description
    SpaceNet 7 Test Source Imagery
    Resource type
    Source Imagery
    Collection ID
    sn7_test_source
    License
    CC-BY-SA-4.0

Edit this dataset entry on GitHub

Home