{"id":4,"date":"2011-12-08T11:55:34","date_gmt":"2011-12-08T10:55:34","guid":{"rendered":"http:\/\/project.inria.fr\/template1\/?page_id=4"},"modified":"2024-09-27T13:24:09","modified_gmt":"2024-09-27T11:24:09","slug":"roofsat-dataset","status":"publish","type":"page","link":"https:\/\/project.inria.fr\/roofsat\/","title":{"rendered":"The RoofSat dataset"},"content":{"rendered":"<p>RoofSat is a dataset&nbsp; for representing roofs as wireframes in satellite images. The dataset is composed of 550 images of 550&#215;550 pixels representing urban scene at nadir. They originate from 11 Pleiades Neo satellite Images at 30cm resolution, from which data augmentation has been performed with rotation, scaling, translation, noise, blurring and contrast variation. These images present various types of urban scenes , i.e. residential, urban dense and industrial. The wireframes representing both contours and roof-skeletons of buildings under the form of planar graphs.<\/p>\n\n\n<p><\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Data<\/h3>\n\n\n\n<p>This dataset contains four folders of data:<\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>img: grayscale images from panchromatic satellite images<\/li><li>img_color: colored images from pansharpened satellite images<\/li><li>gt: corresponding ground-truth wireframe of images in NPZ format under &#8216;lines&#8217; key, with [[point1_x, point1_y],[point2_x, point2_y]] formalism for line-segments<\/li><li>building_masks: corresponding building masks of images<\/li><\/ul>\n\n\n\n<p>Here is an exemple of each data available for one of the image:<\/p>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-9d6595d7 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-full is-resized\"><a href=\"https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100.png\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100.png\" alt=\"\" class=\"wp-image-97\" width=\"283\" height=\"283\" srcset=\"https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100.png 550w, https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-300x300.png 300w, https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-150x150.png 150w\" sizes=\"auto, (max-width: 283px) 100vw, 283px\" \/><\/a><\/figure><\/div>\n\n\n\n<p class=\"has-text-align-center\"><em>Grayscale image<\/em><\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-full is-resized\"><a href=\"https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-2.png\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-2.png\" alt=\"\" class=\"wp-image-99\" width=\"282\" height=\"282\" srcset=\"https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-2.png 550w, https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-2-300x300.png 300w, https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-2-150x150.png 150w\" sizes=\"auto, (max-width: 282px) 100vw, 282px\" \/><\/a><\/figure><\/div>\n\n\n\n<p class=\"has-text-align-center\"><em>Colored image<\/em><\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-9d6595d7 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-full is-resized\"><a href=\"https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-3.png\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-3.png\" alt=\"\" class=\"wp-image-102\" width=\"280\" height=\"280\" srcset=\"https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-3.png 550w, https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-3-300x300.png 300w, https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-3-150x150.png 150w\" sizes=\"auto, (max-width: 280px) 100vw, 280px\" \/><\/a><\/figure><\/div>\n\n\n\n<p class=\"has-text-align-center\">G<em>rayscale image with ground truth wireframe<\/em><\/p>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-full is-resized\"><a href=\"https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-1.png\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-1.png\" alt=\"\" class=\"wp-image-98\" width=\"280\" height=\"280\" srcset=\"https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-1.png 550w, https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-1-300x300.png 300w, https:\/\/project.inria.fr\/roofsat\/files\/2024\/07\/0100-1-150x150.png 150w\" sizes=\"auto, (max-width: 280px) 100vw, 280px\" \/><\/a><\/figure><\/div>\n\n\n\n<p class=\"has-text-align-center\"><em>Building mask<\/em><\/p>\n<\/div>\n<\/div>\n\n\n\n<h3 class=\"wp-block-heading\">Download<\/h3>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-9d6595d7 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:100%\">\n<p>Click <strong><a href=\"http:\/\/www-sop.inria.fr\/members\/Florent.Lafarge\/benchmark\/Roofsat.zip\">HERE<\/a><\/strong> to download the dataset (408Mo)<\/p>\n<\/div>\n<\/div>\n\n\n\n<h3 class=\"wp-block-heading\">Citation<\/h3>\n\n\n\n<p>This dataset is a contribution of the paper &#8216;<a href=\"https:\/\/hal.science\/hal-04648268\/file\/Marion_ECCV24.pdf\">LineFit: A Geometric Approach for Fitting Line Segments in Images<\/a>\u2019 by Marion Boyer, David Youssefi and Florent Lafarge, presented at ECCV 2024. Please refer to this paper if you use the dataset.<\/p>\n\n\n\n<p><\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Copyright<\/h3>\n\n\n\n<p>This dataset can be used for research purposes only. The original Pleiades Neo images are copyrighted by AIRBUS DS.<\/p>","protected":false},"excerpt":{"rendered":"<p>RoofSat is a dataset&nbsp; for representing roofs as wireframes in satellite images. The dataset is composed of 550 images of 550&#215;550 pixels representing urban scene at nadir. They originate from 11 Pleiades Neo satellite Images at 30cm resolution, from which data augmentation has been performed with rotation, scaling, translation, noise,\u2026<\/p>\n<p> <a class=\"continue-reading-link\" href=\"https:\/\/project.inria.fr\/roofsat\/\"><span>Continue reading<\/span><i class=\"crycon-right-dir\"><\/i><\/a> <\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-4","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/project.inria.fr\/roofsat\/wp-json\/wp\/v2\/pages\/4","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/project.inria.fr\/roofsat\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/project.inria.fr\/roofsat\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/roofsat\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/roofsat\/wp-json\/wp\/v2\/comments?post=4"}],"version-history":[{"count":22,"href":"https:\/\/project.inria.fr\/roofsat\/wp-json\/wp\/v2\/pages\/4\/revisions"}],"predecessor-version":[{"id":139,"href":"https:\/\/project.inria.fr\/roofsat\/wp-json\/wp\/v2\/pages\/4\/revisions\/139"}],"wp:attachment":[{"href":"https:\/\/project.inria.fr\/roofsat\/wp-json\/wp\/v2\/media?parent=4"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}