Christchurch Aerial Semantic Dataset

<p>&nbsp;</p> <p>The <strong>Christchurch Aerial Semantic Dataset (CASD)</strong> comprises aerial imagery at very high resolution over Christchurch, New-Zealand, and reference semantic data for urban objects such as buildings, vegetation and vehicles.</p> <p>It aims to foster developments of new methods for Earth observation including automatic image classification, object detection, semantic segmentation, semi-supervised learning, etc...</p> <p><strong>Aerial imagery</strong> consists in the Christchurch Earthquake Imagery dataset, released by Land Information New Zealand:</p> <p><a href="https://www.linz.govt.nz/land/maps/linz-topographic-maps/imagery-orthophotos/christchurch-earthquake-imagery">https://www.linz.govt.nz/land/maps/linz-topographic-maps/imagery-orthophotos/christchurch-earthquake-imagery</a></p> <p><strong>Annotations</strong> were produced by ONERA/DTIS on 4 images. Three classes were tagged: buildings (797 objects), cars (2357 objects), and vegetation (938 objects). All objects are given as polygonal bounding boxes (shapefiles) and image semantic masks (rasters).</p> <p>&nbsp;</p> <p><strong>License</strong></p> <p>This imagery is licensed under a Creative Commons Attribution 4.0 International licence (<a href="https://creativecommons.org/licenses/by/4.0/">https://creativecommons.org/licenses/by/4.0/</a>) with Crown copyright reserved. This means anyone is free to copy, distribute, and adapt the imagery so long as it is attributed to the Crown, eg &rdquo;Crown Copyright Reserved.&rdquo;</p> <p>The annotations are licensed also under a Creative Commons Attribution 4.0 International licence (<a href="https://creativecommons.org/licenses/by/4.0/">https://creativecommons.org/licenses/by/4.0/</a>) with authors&rsquo; and ONERA copyright reserved. This means anyone is free to copy, distribute, and adapt the annotations as long as they are attributed to the authors and ONERA.</p> <p>For research papers, acknowledgments can be done by citing the authors&rsquo; works:</p> <p><em>H. Randrianarivo, B. Le Saux, and M. Ferecatu. Man-made structure detection with deformable part-based models. In IEEE Int. Geoscience and Remote Sensing Symposium (IGARSS), Melbourne, Australia, July 2013</em></p> <p><em>N. Audebert, B. Le Saux, and S. Lef&egrave;vre. Segment-before-Detect: Vehicle Detection and Classification through Semantic Segmentation of Aerial Images. Remote Sensing, 9(4):1&ndash;18, April 2017</em></p> <p>&nbsp;</p>