Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
7
datasets available to search
ShareScore release 0.9.0
Dataset results
7 results for “building footprint”
Building footprints Oldenburg derived from aerial imagery
<p>This data set contains about 78000 georeferenced polygons representing all building footprints within the administrative boundaries of the city of Oldenburg, Lower Saxony, Germany. These geometries were created by a deep learning-based image segmentation. The model for this was trained at the State Office of Lower Saxony for Geoinformation and Surveying (LGLN).</p> <p>We publish this data under the CC0 license. <br>You can do whatever you want with it. There are no restrictions.<br><br>If you do something great with the data set, we'd love to hear about it: <a href="mailto:ki-gebaeudeerkennung@geolabs.atlassian.net">ki-gebaeudeerkennung@geolabs.atlassian.net</a><br>If you use this dataset, you are welcome to reference it - but you don't have to.<br>Would you like builiding footprints for another area? We'd love to hear about it.</p>
Reference Datasets for: SHAFTS (v2022.3): a deep-learning-based Python package for Simultaneous extraction of building Height And FootprinT from Sentinel Imagery
<p>These are reference building height and footprint datasets which consist of 46 cities worldwide and support the development of SHAFTS (https://github.com/LllC-mmd/3DBuildingInfoMap).</p> <p>The snapshot of original reference datasets from 46 cities and related GitHub repository has been created as a zipped file named <strong><em>SHAFTS_220527_snapshot.zip</em></strong>.</p> <p>On 2022.5.27, we added 8 additional cities from ArcGIS Hub when compared with the previous version (https://doi.org/10.5281/zenodo.6370003).</p>
ETHOS.BUILDA: Building Footprint and Height Dataset Germany
<h2>Introduction</h2> <p>This dataset contains all buildings in Germany with their footprint polygon and height. It is a partial dump of the ETHOS.BUILDA database (version v7_20240429). ETHOS.BUILDA is a database containing building-level data for the German building stock. It is based on various data sources that are combined and enriched with machine learning approaches to generate one consistent and complete building dataset. </p> <p>ETHOS.BUILDA is made available under the <a href="http://opendatacommons.org/licenses/odbl/1.0" target="_blank" rel="noopener">Open Database License (ODbL)</a>. The licenses of the contents of the database depend on the data source. The sources of the building attributes and information on the type of processing that was done to assign the information from the raw data to the building in ETHOS.BUILDA are provided for each individual data point.</p> <h2>Data structure and file overview</h2> <p>Building data is provided per federal state, the files are named according to the <a href="https://en.wikipedia.org/wiki/NUTS_statistical_regions_of_Germany" target="_blank" rel="noopener">NUTS-1</a> region names. The building data has the following fields:</p> <table> <tbody> <tr> <td><strong>field name</strong></td> <td><strong>description</strong></td> </tr> <tr> <td>ID</td> <td>unique identifier of the building</td> </tr> <tr> <td>source</td> <td>the source of the building footprint</td> </tr> <tr> <td>footprint</td> <td>footprint polygon in WKT-format, EPSG:3035</td> </tr> <tr> <td>height_m</td> <td> <p>value: height of the building in [m], </p> <p>source: source of the height data,</p> <p>lineage: height assignment method</p> </td> </tr> </tbody> </table> <p>A mapping of the abbreviations of "source" and "lineage" of individual data points to the descriptions is provided in sources.csv and lineages.csv. There is no source entry for the source "v7_model.json" in the sources.csv file, as this refers to the internally trained machine learning model and not to an external dataset.</p> <h2>Acknowledgements</h2> <p>This work was supported by the Helmholtz Association under the program "Energy System Design". </p> <p>Furthermore, the authors would like to express their gratitude to the Federal Ministry for Economic Affairs and Climate Action (BMWK.IIB4) for providing the necessary resources to conduct this study. Our research was supported by the WAAGE Grant Program (Grant No. 03EI1044/03EE 5031D), and we appreciate their financial assistance.</p>
Photovoltaic Windows to Offset the Intensive Energy and Carbon Footprints of Highly Glazed Buildings
<p>Data generated by extensive building energy simulations to determine the impact of next-generation glazing technologies.</p>
China's first sub-meter building footprints derived by deep learning (part 2 of 2).
<h1><strong>Download</strong></h1> <p>Due to Zenodo's file size limitations, we are releasing <strong>different parts</strong> of CBF and GBD in <strong>different versions</strong>. See the below for specific information:</p> <p><strong>1. China's first sub-meter building footprints (CBF) derived by deep learning:</strong></p> <ul> <li>part1: version12 (v12), City 1 to 210, <a href="https://doi.org/10.5281/zenodo.10473278">https://doi.org/10.5281/zenodo.10473278</a></li> <li>part2: version13 (v13), City 211 to 356, <a href="https://doi.org/10.5281/zenodo.10475803">https://doi.org/10.5281/zenodo.10475803 <strong>(current version)</strong></a></li> </ul> <p> <strong>Building attributes:</strong></p> <ul> <li>id: Index number of the current building.</li> <li>year: Year of construction retrieved from GISA.</li> <li>height_mean: The average height of the building (computed from the pixels within the building footprint) obtained from CNBH (meters).</li> <li>height_max: Maximum height of the building (based on the highest pixel value within the building footprint) obtained from CNBH (meters).</li> <li>height_min: Minimum height of the building (based on the lowest pixel value within the building footprint) obtained from CNBH (meters).</li> <li>miniDist: Shortest straight-line distance to another building.</li> <li>dist_id: Index number of the building with the shortest straight-line distance to the current building.</li> <li>area: Area of the current building (square meters).</li> <li>perimeter: Perimeter of the current building (meters).</li> <li>inurban_19: A value of 1 indicates that the building was situated in an urban area in 1990, while a value of 0 signifies that it was located in a rural area in 1990. This determination is made using GUB data.</li> <li>inurban_1: A value of 1 indicates that the building was situated in an urban area in 1995, while a value of 0 signifies that it was located in a rural area in 1995. This determination is made using GUB data.</li> <li>inurban_20: A value of 1 indicates that the building was situated in an urban area in 2000, while a value of 0 signifies that it was located in a rural area in 2000. This determination is made using GUB data.</li> <li>inurban_2: A value of 1 indicates that the building was situated in an urban area in 2005, while a value of 0 signifies that it was located in a rural area in 2005. This determination is made using GUB data.</li> <li>inurban_3: A value of 1 indicates that the building was situated in an urban area in 2010, while a value of 0 signifies that it was located in a rural area in 2010. This determination is made using GUB data.</li> <li>inurban_4: A value of 1 indicates that the building was situated in an urban area in 2015, while a value of 0 signifies that it was located in a rural area in 2015. This determination is made using GUB data.</li> <li>inurban_5: A value of 1 indicates that the building was situated in an urban area in 2020, while a value of 0 signifies that it was located in a rural area in 2020. This determination is made using GUB data.</li> </ul> <p> </p> <p><strong>2. Global Building Dataset (GBD):</strong></p> <p>This dataset comprises approximately 800,000 images(512*512) with diverse architectural styles worldwide. It can be served as training and test samples for building extraction in different regions globally. In order to enhance usability, we did not break the continuity of the image and published it in 1024*1024 size.</p> <table> <tbody> <tr> <td>Version</td> <td>description</td> <td>link</td> </tr> <tr> <td>v1</td> <td>All labels. Images of Africa, Australia, and South America.</td> <td><a href="../records/10043352">https://zenodo.org/records/10043352</a></td> </tr> <tr> <td>v2</td> <td>image of Asia (part 1 to 30 of 53).</td> <td><a href="../records/10456238">https://zenodo.org/records/10456238</a></td> </tr> <tr> <td>v3</td> <td>image of Asia (part 31 to 53 of 53).</td> <td><a href="../records/10457368">https://zenodo.org/records/10457368</a></td> </tr> <tr> <td>v4</td> <td>image of Europe (part 1 to 21 of 58).</td> <td><a href="../records/10458273">https://zenodo.org/records/10458273</a></td> </tr> <tr> <td>v5</td> <td>image of Europe (part 21 to 42 of 58).</td> <td><a href="../records/10460868">https://zenodo.org/records/10460868</a></td> </tr> <tr> <td>v6</td> <td>image of Europe (part 43 to 58 of 58).</td> <td><a href="../records/10462506">https://zenodo.org/records/10462506</a></td> </tr> <tr> <td>v7</td> <td>image of North America (part 1 to 20 of 93).</td> <td><a href="../records/10463385">https://zenodo.org/records/10463385</a></td> </tr> <tr> <td>v8</td> <td>image of North America (part 21 to 40 of 93).</td> <td><a href="../records/10465076">https://zenodo.org/records/10465076</a></td> </tr> <tr> <td>v9</td> <td>image of North America (part 41 to 60 of 93).</td> <td><a href="../records/10466569">https://zenodo.org/records/10466569</a></td> </tr> <tr> <td>v10</td> <td>image of North America (part 61 to 80 of 93).</td> <td><a href="../records/10467291">https://zenodo.org/records/10467291</a></td> </tr> <tr> <td>v11</td> <td>image of North America (part 81 to 93 of 93).</td> <td><a href="../records/10471557">https://zenodo.org/records/10471557</a></td> </tr> </tbody> </table> <p> </p>
Vector-to-Image Converted Building Footprints for Building Change Detection
<p>This dataset comprises multiple folders designed for building change detection, organized as follows:</p> <p>• <strong>(1) Bounding-box</strong></p> <p>• <strong>Content</strong>: Contains building data generated using the bounding-box method, comprising two subfolders: Changed and Unchanged.</p> <p>• <strong>File Format</strong>: .jpg files, named by ID number.</p> <p>• <strong>(2) Fixed-window</strong></p> <p>• <strong>Content</strong>: Contains building data generated using the fixed-window method, comprising two subfolders: Changed and Unchanged.</p> <p>• <strong>File Format</strong>: .jpg files, named by ID number.</p> <p>• <strong>(3) Displacement</strong></p> <p>• <strong>Content</strong>: Image files containing building displacement information, comprising two subfolders: Displaced and Non-Displaced.</p> <p>• <strong>File Format</strong>: .jpg files, generated using the bounding-box method.</p> <p>• <strong>(4) Discrepancy</strong></p> <p>• <strong>Content</strong>: Image files containing building discrepancy information, comprising two subfolders: Significant and Non-Significant.</p> <p>• <strong>File Format</strong>: .jpg files, generated with a focus on the areas of significant difference.</p>
California building footprints
Open the record for dataset details and reuse information.
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.