SlumMapVisionBR: A Dataset for Mapping Slums with Medium-Resolution Satellite Imagery

<p>This dataset contains Landsat images (30m/pixel) and masks with slum locations in Brazil.&nbsp;</p><p>This imagery can be used to train models that help keep track of Goal 11.1 of the United Nations Sustainable Development Goals.&nbsp;</p><p>Details on how the data was collected and labelled are available at:&nbsp;<a href="https://github.com/ml-labs-crt/SlumMapVisionBR">https://github.com/ml-labs-crt/SlumMapVisionBR</a>, along with the code to generate the dataset and benchmark results.</p><p>Description of files:</p><ul><li>images.zip contains the images.</li><li>masks.zip contains the masks with slum locations (1 indicates the area has been labelled as a slum).</li><li>metadata.csv contains information about the 116 locations in this dataset.</li><li>metadata_dictionary.txt includes a description of the fields in metadata.csv.</li></ul><p><strong>Refining documentation:</strong>&nbsp;We welcome additions and edits that make using the existing data or adding new data more straightforward for the community. Please get in touch with us by <a href="https://github.com/ml-labs-crt/SlumMapVisionBR/issues">posting an issue on GitHub</a>.</p>