{"id":29,"date":"2026-09-22T21:01:41","date_gmt":"2026-09-22T21:01:41","guid":{"rendered":"https:\/\/cityatlas.org\/methods\/?p=29"},"modified":"2026-09-22T22:30:47","modified_gmt":"2026-09-22T22:30:47","slug":"image-classification","status":"publish","type":"post","link":"https:\/\/cityatlas.org\/methods\/notes\/image-classification\/","title":{"rendered":"Image Classification"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">The project has 2 foundational datasets: 2025 satellite imagery and 1977 Soviet topographic maps. Quick categorization of patterns does not seem possible.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">What should be possible is to use Esri&#8217;s Image Classification tools to divide the main land use patterns that are visible on the maps:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Steep areas denoted by closely spaced orange topo lines<\/li>\n\n\n\n<li>Green forested areas. Often steep, so therefore there is a forested and steep class, and a forested and not steep class<\/li>\n\n\n\n<li>Urbanized areas symbolized with orange street blocks &#8211;with the background white of the map serving as street grid<\/li>\n\n\n\n<li>Smaller towns and major structures denoted by black rectilinear polygons<\/li>\n\n\n\n<li>Cyrillic labels. Which I would love to ignore<\/li>\n\n\n\n<li>And of course, blue for water.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">Highways, roads, rivers, and streams round out the linear features. There are also labeled and unlabeled point symbols. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">It took a lot of fiddling, but today I think the best approach is to use the segmentation tool multiple times to pick up different types of classes. I&#8217;m working on a spatially coarse run through right now, attempting to pull out cities vs steep areas. They use the same color of ink. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Below, a detail of the Wuhan sheet shows wooded and unwooded areas adjacent to urbanized Wuchang. <\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"744\" height=\"265\" src=\"https:\/\/cityatlas.org\/methods\/wp-content\/uploads\/2026\/09\/image-3.png\" alt=\"\" class=\"wp-image-30\" srcset=\"https:\/\/cityatlas.org\/methods\/wp-content\/uploads\/2026\/09\/image-3.png 744w, https:\/\/cityatlas.org\/methods\/wp-content\/uploads\/2026\/09\/image-3-300x107.png 300w\" sizes=\"auto, (max-width: 744px) 100vw, 744px\" \/><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\"> <\/p>\n","protected":false},"excerpt":{"rendered":"<p>The project has 2 foundational datasets: 2025 satellite imagery and 1977 Soviet topographic maps. Quick categorization of patterns does not seem possible. What should be possible is to use Esri&#8217;s Image Classification tools to divide the main land use patterns that are visible on the maps: Highways, roads, rivers, and streams round out the linear [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":30,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_feature_clip_id":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_post_was_ever_published":false},"categories":[3],"tags":[],"class_list":["post-29","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-notes"],"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"https:\/\/cityatlas.org\/methods\/wp-content\/uploads\/2026\/09\/image-3.png","_links":{"self":[{"href":"https:\/\/cityatlas.org\/methods\/wp-json\/wp\/v2\/posts\/29","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cityatlas.org\/methods\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cityatlas.org\/methods\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/cityatlas.org\/methods\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/cityatlas.org\/methods\/wp-json\/wp\/v2\/comments?post=29"}],"version-history":[{"count":1,"href":"https:\/\/cityatlas.org\/methods\/wp-json\/wp\/v2\/posts\/29\/revisions"}],"predecessor-version":[{"id":31,"href":"https:\/\/cityatlas.org\/methods\/wp-json\/wp\/v2\/posts\/29\/revisions\/31"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cityatlas.org\/methods\/wp-json\/wp\/v2\/media\/30"}],"wp:attachment":[{"href":"https:\/\/cityatlas.org\/methods\/wp-json\/wp\/v2\/media?parent=29"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cityatlas.org\/methods\/wp-json\/wp\/v2\/categories?post=29"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cityatlas.org\/methods\/wp-json\/wp\/v2\/tags?post=29"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}