SpaceNet: Accelerating geospatial machine learning SpaceNet Off-Nadir Dataset | SpaceNet on AWS
IARPA CORE3D Public Data Urban 3D Challenge Dataset fMoW Dataset MVS Dataset SpaceNet Off-Nadir Dataset SpaceNet Buildings Dataset V1 SpaceNet Buildings Dataset V2 SpaceNet Imagery SpaceNet POI Dataset SpaceNet Roads Dataset

The SpaceNet Off-Nadir Dataset

The Problem

Can you help us automate mapping from off-nadir imagery? In this challenge, competitors are tasked with finding automated methods for extracting map-ready building footprints from high-resolution satellite imagery from high off-nadir imagery. In many disaster scenarios the first post-event imagery is from a more off-nadir image than is used in standard mapping use cases. The ability to use higher off-nadir imagery will allow for more flexibility in acquiring and using satellite imagery after a disaster. Moving towards more accurate fully automated extraction of building footprints will help bring innovation to computer vision methodologies applied to high-resolution satellite imagery, and ultimately help create better maps where they are needed most.

Your task will be to extract building footprints from increasingly off-nadir satellite images. The polygon’s you create will be compared to ground truth, and the quality of the solutions will be measured using the SpaceNet metric.

The Data - Over 120,000 Building footprints over 665 sqkm of Atlanta, GA with 27 associated WV-2 images.

This dataset contains 27 8-Band WorldView-2 images taken over Atlanta, GA on December 22nd, 2009. They range in off-nadir angle from 7 degrees to 54 degrees.

For the competition, the 27 images are broken into 3 segments based on their off-nadir angle:

The entire set of images was then tiled into 450m x 450m tiles.

See the labeling guide and schema for details about the creation of the dataset

Catalog IDPan ResolutionOff Nadir AngleTarget AzimuthCatgory
1910300100035D1B000.874220.7Very Off-Nadir
201030010003CCD7000.9544.220Very Off-Nadir
211030010003713C001.0346.119.5Very Off-Nadir
2210300100033C52001.1347.819Very Off-Nadir
2310300100034927001.2349.318.5Very Off-Nadir
2410300100039E62001.3650.918Very Off-Nadir
251030010003BDDC001.4852.217.7Very Off-Nadir
261030010003CD43001.6353.417.4Very Off-Nadir
271030010003193D001.675417.4Very Off-Nadir


The data is hosted on AWS as Public Dataset. An AWS account is required.

aws s3 ls s3://spacenet-dataset/SpaceNet_Off-Nadir_Competition/

Sample Data

2 Samples from each Off-Nadir Image - Off-Nadir Imagery Samples

To download processed 450mx450m tiles of AOI_6_Atlanta (728.8 MB) with associated building footprints:

aws s3 cp s3://spacenet-dataset/Spacenet_Off-Nadir_Dataset/SpaceNet-Off-Nadir_Sample/SpaceNet-Off-Nadir_Sample.tar.gz

Training Data

SpaceNet Off-Nadir Training Base Directory:

aws s3 ls s3://spacenet-dataset/SpaceNet_Off-Nadir_Dataset/SpaceNet-Off-Nadir_Train/

SpaceNet Off-Nadir Building Footprint Extraction Training Data Labels (15 mb)

aws s3 cp s3://spacenet-dataset/SpaceNet_Off-Nadir_Dataset/SpaceNet-Off-Nadir_Train/geojson.tar.gz .

SpaceNet Off-Nadir Building Footprint Extraction Training Data Imagery (186 GB)

To download processed 450mx450m tiles of AOI 6 Atlanta.

Each of the 27 Collects forms a separate .tar.gz labeled “Atlanta_nadir{nadir-angle}_catid_{catid}.tar.gz”. Each .tar.gz is ~7 GB

aws s3 cp s3://spacenet-dataset/SpaceNet_Off-Nadir_Dataset/SpaceNet-Off-Nadir_Train/ . --exclude "*geojson.tar.gz" --recursive

Test Data

AOI 6 Atlanta - Building Footprint Extraction Testing Data

To download processed 450mx450m tiles of AOI 6 Atlanta (5.8 GB):

aws s3 cp s3://spacenet-dataset/SpaceNet_Off-Nadir_Dataset/SpaceNet-Off-Nadir_Test/SpaceNet-Off-Nadir_Test_Public.tar.gz .

The Metric

In the SpaceNet Off-Nadir Building Extraction Challenge, the metric for ranking entries is the SpaceNet Metric.
This metric is an F1-Score based on the intersection over union of two building footprints with a threshold of 0.5

F1-Score is calculated by taking the total True Positives, False Positives, and False Negatives for each nadir segement and then averaging the F1-Score for each segement.

F1-Score Total = mean(F1-Score-Nadir, F1-Score-Off-Nadir, F1-Score-Very-Off-Nadir)

Competition Updates:

For information about the currently running challenge visit the competition site on topcoder.

For more details about previous SpaceNet Building Challenges SpaceNet Building Extraction Challenge: Round 2 visit it’s website

Check out CosmiQ Work’s Blog, The DownLinQ or follow the SpaceNetUtilities Github Page


Creative Commons License
The SpaceNet Dataset by SpaceNet Partners is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.