SpaceNet 6 Challenge Launch
--
Preface: SpaceNet LLC is a nonprofit organization dedicated to accelerating open source, artificial intelligence applied research for geospatial applications, specifically foundational mapping (i.e. building footprint & road network detection). SpaceNet is run in collaboration with CosmiQ Works, Maxar Technologies, Intel AI, Amazon Web Services (AWS), Capella Space, Topcoder, and IEEE GRSS.
The SpaceNet 6 challenge is officially live, and offering $50,000 in cash prizes to our top participants! In the SpaceNet 6 challenge, participants are asked to automatically extract building footprints with computer vision and artificial intelligence (AI) algorithms using a combination of Capella Space synthetic aperture radar (SAR) and electro-optical satellite imagery from Maxar. The challenge will run from March 16th until May 1st. Top participants will be invited to share their work at CVPR EarthVision in Seattle, Washington on June 14th, 2020.
Register and compete in the challenge on TopCoder:
https://www.topcoder.com/spacenet
Learn more about SpaceNet:
Win AWS Credits:
The first 30 participants to achieve an F1 Score of 0.2 on the public leaderboard (recall that the the SpaceNet 6 baseline (link: https://medium.com/the-downlinq/the-spacenet-6-baseline-3b8ae8068351) achieved a score of 0.21) will be eligible to receive an AWS credit worth $500 in compute time.
Download the dataset from our AWS S3 Bucket for free:
aws s3 cp s3://spacenet-dataset/spacenet/SN6_buildings/tarballs/SN6_buildings_AOI_11_Rotterdam_train.tar.gz .Read about or try out the baseline:
We recently released a new baseline algorithm, which could be used as an example or starting point for SpaceNet 6 participants for extracting building footprints from SAR imagery.
git clone https://github.com/CosmiQ/CosmiQ_SN6_Baseline/Important Dates:
March 16th — Challenge Launch
April 17th — Challenge Midpoint
May 1st — Challenge Ends
June 4th — Winners Announced
June 14th — CVPR EarthVision
What’s Next?
As always, stay tuned to The DownLinQ and check out https://spacenet.ai for more details on the dataset and challenge.
