Menu

spacenet.ai

Accelerating Geospatial Machine Learning

Geo Datasets

Atlanta

By

Datasets // Atlanta

SpaceNet AOI 6 – Atlanta

Catalog ID: Off-Nadir Building Detection
Image Time: 2009-12-22

SpaceNet Simple Storage Service (S3) Directory Structure (AOI 6)


AOIs
├── AOI_6_Atlanta
│   │
│   ├── nadir7_catid_1030010003D22F00                          # Raw source geotiffs for collect 1030010003D22F00
│   │   │
│   │   ├── MS                                                 # Raw source geotiffs of 8-Band Multi-Spectral raster data from WorldView-2
│   │   ├── PAN                                                # Raw source geotiffs of Panchromatic raster data from Worldview-2
│   │   └── PS-RGBNIR                                          # Raw source geotiffs of RGB+NIR raster data from Worldview-2 pansharpened to 0.5m
│   │
│   ├── nadir8_catid_10300100023BC100                          # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 10300100023BC100
│   ├── nadir10_catid_1030010003993E00                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003993E00
│   ├── nadir10_catid_1030010003CAF100                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003CAF100
│   ├── nadir13_catid_1030010002B7D800                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010002B7D800
│   ├── nadir14_catid_10300100039AB000                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 10300100039AB000
│   ├── nadir16_catid_1030010002649200                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010002649200
│   ├── nadir19_catid_1030010003C92000                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003C92000
│   ├── nadir21_catid_1030010003127500                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003127500
│   ├── nadir23_catid_103001000352C200                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 103001000352C200
│   ├── nadir25_catid_103001000307D800                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 103001000307D800
│   ├── nadir27_catid_1030010003472200                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003472200
│   ├── nadir29_catid_1030010003315300                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003315300
│   ├── nadir30_catid_10300100036D5200                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 10300100036D5200
│   ├── nadir32_catid_103001000392F600                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 103001000392F600
│   ├── nadir34_catid_1030010003697400                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003697400
│   ├── nadir36_catid_1030010003895500                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003895500
│   ├── nadir39_catid_1030010003832800                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003832800
│   ├── nadir42_catid_10300100035D1B00                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 10300100035D1B00
│   ├── nadir44_catid_1030010003CCD700                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003CCD700
│   ├── nadir46_catid_1030010003713C00                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003713C00
│   ├── nadir47_catid_10300100033C5200                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 10300100033C5200
│   ├── nadir49_catid_1030010003492700                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003492700
│   ├── nadir50_catid_10300100039E6200                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 10300100039E6200
│   ├── nadir52_catid_1030010003BDDC00                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003BDDC00
│   ├── nadir53_catid_1030010003193D00                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003193D00
│   ├── nadir53_catid_1030010003CD4300                         # Raw source geotiffs (divided as shown in the nadir7 collect) for collect 1030010003CD4300
│   │
│   └── metadata                                               # Collection metadata for the above collects
│
spacenet
└── SN4_buildings
    │
    ├── tarballs
    │   │
    │   ├── train
    │   │   │
    │   │   ├── Atlanta_nadir7_catid_1030010003D22F00.tar.gz   # Tiled source geotiffs for collect
    │   │   ├── Atlanta_nadir8_catid_10300100023BC100.tar.gz
    │   │   ├── Atlanta_nadir10_catid_1030010003993E00.tar.gz
    │   │   ├── [etc.]
    │   │   └── geojson.tar.gz                                 # Building footprint label geojsons for the training dataset
    │   │
    │   ├── SpaceNet-Off-Nadir_Test_Public.tar.gz              # Public test imagery from all 27 collects 
    │   └── SpaceNet-Off-Nadir_Sample.tar.gz                   # Sample imagery and labels for the SpaceNet 4: Off-nadir building footprint extraction challenge
    │
    ├── train                                                  # Tiled training imagery and building footprint labels
    │   │
    │   └── AOI_6_Atlanta
    │       │
    │       ├── nadir7_catid_1030010003D22F00                  # Tiled geotiffs for collect 1030010003D22F00
    │       │   │
    │       │   ├── MS                                         # Tiled geotiffs of 8-Band Multi-Spectral raster data from WorldView-2
    │       │   ├── PAN                                        # Tiled geotiffs of Panchromatic raster data from Worldview-2
    │       │   └── PS-RGBNIR                                  # Tiled geotiffs of RGB+NIR raster data from Worldview-2 pansharpened to 0.5m
    │       │
    │       ├── nadir8_catid_10300100023BC100
    │       ├── nadir10_catid_1030010003993E00
    │       ├── nadir10_catid_1030010003CAF100
    │       ├── nadir13_catid_1030010002B7D800
    │       ├── [etc.]
    │       └── geojson_buildings                              # Tiled building footprint label geojsons for the training dataset
    │
    └── test_public                                            # Tiled public test set images and building footprint labels
        │
        └── AOI_6_Atlanta # Public test imagery from all 27 collects
            ├── nadir7_catid_1030010003D22F00                  # Tiled public test set geotiffs for collect 1030010003D22F00
            │   │
            │   ├── MS                                         # Tiled public test set geotiffs of 8-Band Multi-Spectral raster data from WorldView-2
            │   ├── PAN                                        # Tiled public test set geotiffs of Panchromatic raster data from Worldview-2
            │   └── PS-RGBNIR                                  # Tiled public test set geotiffs of RGB+NIR raster data from Worldview-2 pansharpened to 0.5m
            │
            ├── nadir8_catid_10300100023BC100
            ├── nadir10_catid_1030010003993E00
            ├── nadir10_catid_1030010003CAF100
            ├── nadir13_catid_1030010002B7D800
            └── [etc.]

Atlanta // Buildings Dataset Resources

AOI 6 – Atlanta – Building Footprint Extraction Training

The path to the processed 450mx450m tiles of AOI 6 with associated building footprint labels for training is:

s3://spacenet-dataset/spacenet/SN4_buildings/tarballs/train/

Khartoum

By

Datasets // Khartoum

SpaceNet AOI 5 – Khartoum

Catalog ID: 104001000A6A1E00
Image Time: 2015-04-13T08:18:08Z

Download Instructions

To view the contents of the dataset

aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_train_AOI_5_Khartoum_geojson_roads_speed.tar.gz . aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_train_AOI_5_Khartoum.tar.gz . aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/SN2_buildings_train_AOI_5_Khartoum .

SpaceNet Simple Storage Service (S3) Directory Structure (AOI 5)

AOIs
└── AOI_5_Khartoum
    ├── MS             # Raw source geotiffs of 8-Band Multi-Spectral raster data from WorldView-3
    ├── PS-MS          # Raw source geotiffs and COGs of 8-Band Multi-Spectral raster data pansharpened to 0.3m
    ├── PAN            # Raw source geotiffs of Panchromatic raster data from Worldview-3
    ├── PS-RGB         # Raw source geotiffs of RGB raster data from Worldview-3 pansharpened to 0.3m
    ├── metadata       # Collect metadata in .XML format
    └── misc	       # SpaceNet 2 challenge tarballs

Khartoum // Roads Dataset Resources

AOI 5 – Khartoum – Road Network Extraction Training

To download processed 400mx400m tiles of AOI 5 (25 GB) with associated building footprints for training do the following:

aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_train_AOI_5_Khartoum.tar.gz .

AOI 5 – Khartoum – Road Network Extraction Testing

To download processed 400mx400m tiles of AOI 5 (8.1 GB) for testing do:

aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_test_public_AOI_5_Khartoum.tar.gz .

Khartoum // Buildings Dataset Resources

AOI 5 – Khartoum – Building Extraction Training

To download processed 200mx200m tiles of AOI 5 (4.7 GB) with associated building footprints for training do the following:

aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/SN2_buildings_train_AOI_5_Khartoum.tar.gz .

AOI 5 – Khartoum – Building Extraction Testing

To download processed 200mx200m tiles of AOI 5 (1.6 GB) for testing do:

aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/AOI_5_Khartoum_test_public.tar.gz .

Shanghai

By

Datasets // Shanghai

SpaceNet AOI 4 – Shanghai

Catalog ID: 104001000C924900
Image Time: 2015-06-06T02:35:27Z

Download Instructions

To download the contents of the challenge dataset

aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_train_AOI_4_Shanghai_geojson_roads_speed.tar.gz . aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_train_AOI_4_Shanghai.tar.gz . aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/SN2_buildings_train_AOI_4_Shanghai.tar.gz .

SpaceNet Simple Storage Service (S3) Directory Structure (AOI 4)

AOIs
└── AOI_4_Shanghai
    ├── MS             # Raw source geotiffs of 8-Band Multi-Spectral raster data from WorldView-3
    ├── PS-MS          # Raw source geotiffs and COGs of 8-Band Multi-Spectral raster data pansharpened to 0.3m
    ├── PAN            # Raw source geotiffs of Panchromatic raster data from Worldview-3
    ├── PS-RGB         # Raw source geotiffs of RGB raster data from Worldview-3 pansharpened to 0.3m
    ├── metadata       # Collect metadata in .XML format
    └── misc	       # SpaceNet 2 challenge tarballs

Shanghai // Roads Dataset Resources

AOI 4 – Shanghai – Road Network Extraction Training

To download processed 400mx400m tiles of AOI 4 (25 GB) with associated building footprints for training do the following:

aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_train_AOI_4_Shanghai.tar.gz .

AOI 4 – Shanghai – Road Network Extraction Testing

To download processed 400mx400m tiles of AOI 4 (8.1 GB) for testing do:

aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_test_public_AOI_4_Shanghai.tar.gz .

Shanghai // Buildings Dataset Resources

AOI 4 – Shanghai –  Building Extraction Training

To download processed 200mx200m tiles of AOI 4 (23.4 GB) with associated building footprints for training do the following:

aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/SN2_buildings_train_AOI_4_Shanghai.tar.gz .

AOI 4 – Shanghai – Building Extraction Testing

To download processed 200mx200m tiles of AOI 4 (7.7 GB) for testing do:

aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/AOI_4_Shanghai_test_public.tar.gz .

Paris

By

Datasets // Paris

SpaceNet AOI 3 – Paris

Catalog ID: 1040010018805C00
Image Time: 2016-02-29T11:19:13Z

Download Instructions

To view the contents of the dataset

aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_train_AOI_3_Paris_geojson_roads_speed.tar.gz . aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_train_AOI_3_Paris.tar.gz . aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/SN2_buildings_train_AOI_3_Paris.tar.gz .

SpaceNet Simple Storage Service (S3) Directory Structure (AOI 3)

AOIs
└── AOI_3_Paris
    ├── MS/             # Raw source geotiffs of 8-Band Multi-Spectral raster data from WorldView-3
    ├── PS-MS/          # Raw source geotiffs and COGs of 8-Band Multi-Spectral raster data pansharpened to 0.3m
    ├── PAN/            # Raw source geotiffs of Panchromatic raster data from Worldview-3
    ├── PS-RGB/         # Raw source geotiffs of RGB raster data from Worldview-3 pansharpened to 0.3m
    ├── metadata/       # Collect metadata in .XML format
    └── misc/		# SpaceNet 2 challenge tarballs

Paris // Roads Dataset Resources

AOI 3 – Paris – Road Network Extraction Training

To download processed 400mx400m tiles of AOI 3 (5.6 GB) with associated building footprints for training do the following:

aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_train_AOI_3_Paris.tar.gz .

AOI 3 – Paris – Road Network Extraction Testing

To download processed 400mx400m tiles of AOI 3 (1.9 GB) for testing do:

aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_test_public_AOI_3_Paris.tar.gz .

Paris // Buildings Dataset Resources

AOI 3 – Paris – Building Extraction Training

To download processed 200mx200m tiles of AOI 3 (5.3 GB) with associated building footprints for training do the following:

aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/SN2_buildings_train_AOI_3_Paris.tar.gz .

AOI 3 – Paris – Building Extraction Testing

To download processed 200mx200m tiles of AOI 3 (1.8 GB) for testing do:

aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/AOI_3_Paris_test_public.tar.gz .

Las Vegas

By

Las Vegas

SpaceNet AOI 2 – Las Vegas

Catalog ID: 10400100137F4900
Image Time: 2015-10-22T18:36:56Z

Download Instructions

To view the contents of the dataset

aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_train_AOI_2_Vegas_geojson_roads_speed.tar.gz . aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_train_AOI_2_Vegas.tar.gz . aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/SN2_buildings_train_AOI_2_Vegas.tar.gz .

SpaceNet Simple Storage Service (S3) Directory Structure (AOI 2)

AOIs
└── AOI_2_Vegas
    ├── MS             # Raw source geotiffs of 8-Band Multi-Spectral raster data from WorldView-3
    ├── PS-MS          # Raw source geotiffs and COGs of 8-Band Multi-Spectral raster data pansharpened to 0.3m
    ├── PAN            # Raw source geotiffs of Panchromatic raster data from Worldview-3
    ├── PS-RGB         # Raw source geotiffs of RGB raster data from Worldview-3 pansharpened to 0.3m
    ├── metadata       # Collect metadata in .XML format
    └── misc	       # SpaceNet 2 challenge tarballs

Las Vegas // Roads Dataset Resources

AOI 2 – Vegas – Road Network Extraction Training

To download processed 400mx400m tiles of AOI 2 (25 GB) with associated building footprints for training do the following:

aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_train_AOI_2_Vegas.tar.gz .

AOI 2 – Vegas – Road Network Extraction Testing

To download processed 400mx400m tiles of AOI 2 (8.1 GB) for testing do:

aws s3 cp s3://spacenet-dataset/spacenet/SN3_roads/tarballs/SN3_roads_test_public_AOI_2_Vegas.tar.gz .

Las Vegas // Buildings Dataset Resources

AOI 2 – Vegas – Building Extraction Training

To download processed 200mx200m tiles of AOI 2 (23 GB) with associated building footprints for training do the following:

aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/SN2_buildings_train_AOI_2_Vegas.tar.gz .

AOI 2 – Vegas – Building Extraction Testing

To download processed 200mx200m tiles of AOI 2 (7.9 GB) for testing do:

aws s3 cp s3://spacenet-dataset/spacenet/SN2_buildings/tarballs/AOI_2_Vegas_test_public.tar.gz .

Rio de Janeiro

By

Rio de Janeiro

SpaceNet AOI 1 – Rio de Janeiro

Catalog ID: ??
Image Time: ??

Download Instructions

To view the contents of the dataset

aws s3 ls s3://spacenet-dataset/AOIs/AOI_1_Rio/

SpaceNet Simple Storage Service (S3) Directory Structure (AOI 1)

s3://spacenet-dataset/
-- AOI_1_Rio
    |-- processedData
    |   -- processedBuildingLabels.tar.gz  # Compressed 3band and 8band 200m x 200m tiles with associated building foot print labels                                 # This dataset is the Training Dataset for the first Top Coder Competition
    `-- srcData
        |-- rasterData
        |   |-- 3-Band.tar.gz # 3band (RGB) Raster Mosaic for Rio De Jenairo area (2784 sq KM) collected by WorldView-2
        |    -- 8-Band.tar.gz # 8band Raster Mosaic for Rio De Jenairo area (2784 sq KM) collected by WorldView-2
         -- vectorData
            |-- Rio_BuildingLabels.tar.gz # Source Dataset that contains Building the building foot prints traced from the Mosaic
            |-- Rio_HGIS_Metro.gdb.tar.gz  # Source Point of Interest Dataset in GeoDatabase Format.  Best if Used with ESRI
             -- Rio_HGIS_Metro_extract.tar # Source Point of Interest Dataset in GeoJSON with associated .jpg.  Easy to Use without ESRI toolset

Rio de Janeiro // Dataset Resources

To download processed 200mx200m tiles of AOI 1 (3.4 GB) with associated building footprints do the following:

aws s3 cp s3://spacenet-dataset/AOIs/AOI_1_Rio/processedData/processedBuildingLabels.tar.gz .

To download the Source Imagery Mosaic (3-band = 2.3 GB and 8-band = 6.5 GB):

aws s3 cp s3://spacenet-dataset/spacenet/SN1_buildings/tarballs/SN1_buildings_train_AOI_1_Rio_3band.tar.gz .
aws s3 cp s3://spacenet-dataset/spacenet/SN1_buildings/tarballs/SN1_buildings_train_AOI_1_Rio_8band.tar.gz .

To download the Source Vector Data (0.18 GB):

aws s3 cp s3://spacenet-dataset/spacenet/SN1_buildings/tarballs/SN1_buildings_train_AOI_1_Rio_geojson_buildings.tar.gz .

Point of Interest Dataset in ESRI GeoDatabase Form (31 GB)

Point of Interest Dataset Extracted into GeoJSONs with associated .jpg (29 GB)