https://github.com/SpaceNetChallenge/SpaceNet7_Multi-Temporal_Solutions

https://github.com/SpaceNetChallenge/SpaceNet7_Multi-Temporal_Solutions

Last synced: about 2 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/SpaceNetChallenge/SpaceNet7_Multi-Temporal_Solutions
• Owner: SpaceNetChallenge
• License: apache-2.0
• Created: 2021-01-29T03:43:37.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2021-01-29T15:54:36.000Z (over 3 years ago)
• Last Synced: 2024-07-23T04:36:03.902Z (about 2 months ago)
• Language: Python
• Size: 10.3 MB
• Stars: 54
• Watchers: 3
• Forks: 22
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-remote-sensing-change-detection - SpaceNetChallenge/SpaceNet7_Multi-Temporal_Solutions

README

        






The SpaceNet 7 Multi-temporal Urban Development Challenge 

Winning Solutions




## Summary

The five subdirectories in this repository comprise the code for the winning solutions of SpaceNet 7 hosted by TopCoder. Each subdirectory contains the competitors' written descriptions of their solution to the challenge. See the blog post on CosmiQ Works' blog [The DownlinQ](?) for an additional summary.  Baseline code can be found [here](https://github.com/CosmiQ/CosmiQ_SN7_Baseline).

Data is hosted on aws at:

```

	s3://spacenet-dataset/spacenet/SN7_buildings/

```

Winning model weights are hosted at:

```

	s3://spacenet-dataset/spacenet-model-weights/spacenet-7/

```

The winning solutions all use Docker, and assume SpaceNet 7 data is mounted in the `/data/` directory.  

Performance of the algorithms on the SpaceNet 7 final test set is shown below:

![alt text](_figs/table1.png)

![alt text](_figs/scot_rate_plot.png)

---------

Questions about SpaceNet? Check out our website at [https://spacenet.ai](https://spacenet.ai).