Chesapeake Land Cover

This dataset contains high-resolution aerial imagery from the USDA NAIP program, high-resolution land cover labels from the Chesapeake Conservancy, low-resolution land cover labels from the USGS NLCD 2011 dataset, low-resolution multi-spectral imagery from Landsat 8, and high-resolution building footprint masks from Microsoft Bing, formatted to accelerate machine learning research read more...

building footprints

land cover

landsat 8

naip

nlcd

segmentation

Open Cities AI Challenge Dataset

This dataset was developed as part of a challenge to segment building footprints from aerial imagery. The goal of the challenge was to accelerate the development of more accurate, relevant, and usable open-source AI models to support mapping for disaster risk management in African cities [Read more about the read more...

building footprints

segmentation

ramp Building Footprint Training Dataset - Accra, Ghana

This chipped training dataset is over Accra and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in read more...

building footprints

object detection

segmentation

ramp Building Footprint Training Dataset - Barishal, Bangladesh

This chipped training dataset is over Barishal and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Bentiu, South Sudan

This chipped training dataset is over Bentiu and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Chittagong, Bangladesh

This chipped training dataset is over Chittagong and parts of the Kutupalong Refugee Camp and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Cox's Bazar, Bangladesh

This chipped training dataset is over Cox's Bazaar and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Dar es Salaam, Tanzania

This chipped training dataset is over Dar es Salaam and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was read more...

building footprints

object detection

segmentation

ramp Building Footprint Training Dataset - Dhaka, Bangladesh

This chipped training dataset is over Dhaka and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Hpa-an, Myanmar

This chipped training dataset is over Hpa-an and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Jashore, Bangladesh

This chipped training dataset is over Jashore and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Karnataka, India

This chipped training dataset is over Karnataka and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Les Cayes, Haiti

This chipped training dataset is over Les Cayes and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Lubumbashi, Democratic Republic of the Congo

This chipped training dataset is over Lubumbashi and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 2 dataset, meaning it has NOT been thoroughly reviewed and improved. This dataset was produced read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Manjama, Sierra Leone

This chipped training dataset is over Manjama and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Mesopotamia, St. Vincent

This chipped training dataset is over Mesopotamia and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Muscat, Oman

This chipped training dataset is over Muscat and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Mzuzu, Malawi

This chipped training dataset is over Mzuzu and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Nairobi, Kenya

This chipped training dataset is over Nairobi and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 2 dataset, meaning it has NOT been thoroughly reviewed and improved. This dataset was produced read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - N'Djamena, Chad

This chipped training dataset is over N'Djamena and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 2 dataset, meaning it has NOT been thoroughly reviewed and improved. This dataset was produced read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Paris, France

This chipped training dataset is over Paris and includes 30cm high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 or smaller pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset read more...

building footprints

object detection

segmentation

worldview-3

ramp Building Footprint Training Dataset - Shanghai, China

This chipped training dataset is over Shanghai and includes 30cm high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 or smaller pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset read more...

building footprints

object detection

segmentation

worldview-3

ramp Building Footprint Training Dataset - Sylhet, Bangladesh

This chipped training dataset is over Sylhet and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 2 dataset, meaning it has NOT been thoroughly reviewed and improved. This dataset was produced read more...

building footprints

maxar

object detection

segmentation

ramp Building Footprint Training Dataset - Wa, Ghana

This chipped training dataset is over Wa and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in read more...

building footprints

maxar

object detection

segmentation

SpaceNet 1

The commercialization of the geospatial industry has led to an explosive amount of data being collected to characterize our changing planet. One area for innovation is the application of computer vision and deep learning to extract information from satellite imagery at scale. CosmiQ Works, Radiant Solutions and NVIDIA have read more...

building footprints

segmentation

worldview-3

SpaceNet 2

The commercialization of the geospatial industry has led to an explosive amount of data being collected to characterize our changing planet. One area for innovation is the application of computer vision and deep learning to extract information from satellite imagery at scale. CosmiQ Works, Radiant Solutions and NVIDIA have read more...

building footprints

segmentation

worldview-3

SpaceNet 4

The commercialization of the geospatial industry has led to an explosive amount of data being collected to characterize our changing planet. One area for innovation is the application of computer vision and deep learning to extract information from satellite imagery at scale. CosmiQ Works, Radiant Solutions and NVIDIA have read more...

building footprints

off-nadir

segmentation

worldview-3

SpaceNet 6

Synthetic Aperture Radar (SAR) is a unique form of radar that can penetrate clouds, collect during all- weather conditions, and capture data day and night. Overhead collects from SAR satellites could be particularly valuable in the quest to aid disaster response in instances where weather and cloud cover can read more...

building footprints

off-nadir

sar

segmentation

worldview-2

SpaceNet 7

The SpaceNet 7 Multi-Temporal Urban Development Challenge aims to help address this deficit and develop novel computer vision methods for non-video time series data. In this challenge, participants will identify and track buildings in satellite imagery time series collected over rapidly urbanizing areas. The competition centers around a new read more...

building footprints

planetscope

segmentation