{"id":12316,"date":"2019-11-22T02:29:24","date_gmt":"2019-11-22T02:29:24","guid":{"rendered":"https:\/\/www.jurn.link\/dazposer\/?p=12316"},"modified":"2019-11-22T02:29:24","modified_gmt":"2019-11-22T02:29:24","slug":"bodypix-2-0","status":"publish","type":"post","link":"https:\/\/jurn.link\/dazposer\/index.php\/2019\/11\/22\/bodypix-2-0\/","title":{"rendered":"BodyPix 2.0"},"content":{"rendered":"<p>Google has released the free <a href=\"https:\/\/blog.tensorflow.org\/2019\/11\/updated-bodypix-2.html\">BodyPix 2.0<\/a>.  This offers automatic identification of people against a relatively noisy  background, and then spots and tracks each person&#8217;s twenty-four body parts.  It then segments, ID&#8217;s and colours each body-part. It can do this even while being fed around 20-25 frames per second, on fairly standard hardware such as an iPhone.<\/p>\n<p><a href=\"https:\/\/www.jurn.link\/dazposer\/oldimages\/demo.jpg\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/www.jurn.link\/dazposer\/oldimages\/demo.jpg\" alt=\"\" width=\"799\" height=\"265\" class=\"alignnone size-full wp-image-12317\" \/><\/a><\/p>\n<p>Version 2.0 adds &#8220;multi-person support and improved accuracy&#8221;. <\/p>\n<p>They also offer the sister-software PoseNet, enabling a basic emulation of what a Kinect does but via standard Webcams&#8230;<\/p>\n<blockquote><p>both BodyPix and PoseNet can be used without installation and just a few lines of code. You don\u2019t need any specialized lenses to use these models \u2014 they work with any basic webcam or mobile camera. And finally users can access these applications by just opening a url. Since all computing is done on device, the data stays private. For all these reasons, we think BodyPix is easily accessible as a tool for artists, creative coders, and those new to programming.<\/p><\/blockquote>\n<p>So&#8230; how to plug this stuff into a nice little DAZ\/Poser-friendly Webcam utility? One that, at the flick of a drop-down menu, will happily real-time puppet and animate any stock figure from an Aiko 3 up to a G8 or La Femme?<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Google has released the free BodyPix 2.0. This offers automatic identification of people against a relatively noisy background, and then spots and tracks each person&#8217;s twenty-four body parts. It then segments, ID&#8217;s and colours each body-part. It can do this even while being fed around 20-25 frames per second, on fairly standard hardware such as [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[17,23,13,9,8,4,7],"tags":[],"class_list":["post-12316","post","type-post","status-publish","format-standard","hentry","category-3d-utilities","category-automation","category-companion-software","category-freebies","category-real-time-animation","category-spotted-in-the-news","category-the-animation-industry"],"_links":{"self":[{"href":"https:\/\/jurn.link\/dazposer\/index.php\/wp-json\/wp\/v2\/posts\/12316","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/jurn.link\/dazposer\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/jurn.link\/dazposer\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/jurn.link\/dazposer\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/jurn.link\/dazposer\/index.php\/wp-json\/wp\/v2\/comments?post=12316"}],"version-history":[{"count":0,"href":"https:\/\/jurn.link\/dazposer\/index.php\/wp-json\/wp\/v2\/posts\/12316\/revisions"}],"wp:attachment":[{"href":"https:\/\/jurn.link\/dazposer\/index.php\/wp-json\/wp\/v2\/media?parent=12316"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jurn.link\/dazposer\/index.php\/wp-json\/wp\/v2\/categories?post=12316"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jurn.link\/dazposer\/index.php\/wp-json\/wp\/v2\/tags?post=12316"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}