SpaceNet_hero_image
AlgorithmChallenges

The SpaceNet Challenge Round 2: Win Big with Automated Mapping



If the SpaceNet Challenge Round 2 were a basketball game, we would just be starting the fourth quarter. This popular Marathon Match — sponsored by CosmiQ Works, DigitalGlobe, and NVIDIA — is challenging the Topcoder Community to develop automated methods for extracting building footprints from high-resolution satellite imagery.
In this challenge, competitors are tasked with finding automated methods for extracting map-ready building footprints from high-resolution satellite imagery. Moving toward more accurate, fully automated extraction of buildings will help bring innovation to computer vision methodologies applied to high-resolution satellite imagery, and ultimately help create better maps where they are most needed.

14268528-0-1mF4M-d8pVElaYRMTswE


This contest is the second edition of the SpaceNet building footprint detection challenge. Most of the problem statement is identical to the specification used in the first challenge. The most important differences are the following:

  • There is much more data, featuring 4 cities

  • There are multiple new imagery formats (i.e., PAN, MUL, RGB-PanSharpen, MUL-PanSharpen)

  • The quality of the building footprint annotations has been improved

  • The length of the competition is longer (2 months)

  • Usage of external data and pretrained models are explicitly allowed

  • Source code and algorithm description of round 1 winners is available

  • Teams are allowed (up to 5 people)

  • The contest is not rated

  • Organizations can participate but will not be eligible for prize money

  • All winning solutions must be submitted as docker containers with all preprocessing and post-processing steps

Large Prizes


Not only are Topcoder members using their algorithm skills to improve the way we use satellite imagery, but they are also making bank. Here is the prize list for this particular Marathon Match:

Prize

USD

1st Place

$6,000

2nd Place

$3,500

3rd Place

$1,500

Best F-score, Las Vegas

$1,000

Best F-score, Paris

$1,000

Best F-score, Shanghai

$1,000

Best F-score, Khartoum

$1,000

Early Incentive**

$1,000

Total Prizes

$15,500


**To win the Early Incentive your solution must be the first to reach a threshold of 400,000 for the average F-score of all the cities.

Scoreboard


Currently there are only 2 members out of the 1,000+ that are registered that have successfully submitted. They are:

wleite
F-Score: 609724.04

<img style="width: 115px;height: 138px" src="https://topcoder-prod-media.s3.amazonaws.com/member/profile/XD_XD-1490091598553.png" />

XD_XD
F-Score: 594583.76

wleite


Although the Early Incentive prize may have already been claimed, there is still an opportunity to earn one or more of the 7 remaining prizes, so get coding and submit today!