{"id":194720,"date":"2025-12-21T09:37:10","date_gmt":"2025-12-21T09:37:10","guid":{"rendered":"https:\/\/www.newsbeep.com\/nz\/194720\/"},"modified":"2025-12-21T09:37:10","modified_gmt":"2025-12-21T09:37:10","slug":"hardware-store-marauders-map-is-clarkian-magic","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/nz\/194720\/","title":{"rendered":"Hardware Store Marauder\u2019s Map Is Clarkian Magic"},"content":{"rendered":"<p>The \u201cMarauder\u2019s Map\u201d is a magical artifact from the Harry Potter franchise. That sort of magic isn\u2019t real, but as Arthur C. Clarke famously pointed out, it doesn\u2019t need to be \u2014 we have technology, and we can make our own magic now. Or, rather, [Dave] on the <a href=\"https:\/\/www.youtube.com\/watch?v=dO32ImnsX-4\" target=\"_blank\" rel=\"nofollow noopener\">YouTube Channel Dave\u2019s Armoury can make it.<\/a><\/p>\n<p>[Dave]\u2019s hardware store might be in a rough neighborhood, since it has 50 cameras\u2019 worth of CCTV coverage. In this case, the stockman\u2019s loss is the hacker\u2019s gain, as [Dave] has talked his way into accessing all of those various camera feeds and is using machine vision to track every single human in the store.<\/p>\n<p>Of course, locating individuals in a video feed is easy \u2014 to locate them in space from that feed, one first needs an accurate map. To do that, [Dave] first 3D scans the entire store with a rover. The scan is in full 3D, and it\u2019s no small amount of data. On the rover, a Jetson AGX is required to handle it; on the bench, a beefy HP Z8 Fury workstation crunches the point cloud into a map. Luckily it came with 500 GB of RAM, since just opening the mesh file generated from that point cloud needs 126 GB. That is processed into a simple 2D floor plan. While the workflow is impressive, we can\u2019t help but wonder if there was an easier way. (Maybe a tape measure?)<\/p>\n<p>Once an accurate map has been generated, it turns out NVIDIA already has a turnkey solution for mapping video feeds to a 2D spatial map. When processing so much data \u2014 remember, there are 50 camera feeds in the store \u2014 it\u2019s not ideal to be passing the image data from RAM to GPU and back again, but luckily NVIDIA\u2019s \u201cDeep Stream\u201d pipeline will do object detection and tracking (including between different video streams) all on the GPU. There\u2019s also pose estimation right in there for more accurate tracking of where a person is standing than just \u201cinside this red box\u201d. With 50 cameras, it\u2019s all a bit much for one card, but luckily [Dave]\u2019s workstation has two GPUs.<\/p>\n<p>Once the coordinates are spat out of the neural networks, it\u2019s relatively simple to put footprints on the map in true Harry Potter fashion. It really is magic, in the Clarkian sense, what you can do if you throw enough computing power at it.<\/p>\n<p>Unfortunately for show-accuracy (or fortunately, if you prefer to avoid gross privacy violations), it doesn\u2019t track every individual by name, but it does demonstrate the possibility with [Dave] and his robot. If you want a map of something\u2026 else\u2026 maybe check out this <a href=\"https:\/\/hackaday.com\/2022\/01\/17\/ai-camera-knows-its-st\/\" rel=\"nofollow noopener\" target=\"_blank\">backyard project<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"The \u201cMarauder\u2019s Map\u201d is a magical artifact from the Harry Potter franchise. That sort of magic isn\u2019t real,&hellip;\n","protected":false},"author":2,"featured_media":194721,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[27],"tags":[156,409,111,139,69],"class_list":["post-194720","post","type-post","status-publish","format-standard","has-post-thumbnail","category-movies","tag-entertainment","tag-movies","tag-new-zealand","tag-newzealand","tag-nz"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts\/194720","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/comments?post=194720"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts\/194720\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/media\/194721"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/media?parent=194720"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/categories?post=194720"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/tags?post=194720"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}