{"id":7217,"date":"2018-07-23T13:59:21","date_gmt":"2018-07-23T20:59:21","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=7217"},"modified":"2019-06-26T22:25:44","modified_gmt":"2019-06-27T05:25:44","slug":"kinemetagraph-used-body-pose-to-drive-search","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2018\/07\/23\/kinemetagraph-used-body-pose-to-drive-search\/","title":{"rendered":"Match your body pose to Hollywood imagery via Kinemetagraph"},"content":{"rendered":"<p>Apropos of Google\u2019s <a href=\"http:\/\/jnack.com\/blog\/2018\/07\/20\/body-rockin-drive-image-search-with-your-body-movements\/\">Move Mirror<\/a> project (mentioned last week), here\u2019s a similar idea:<\/p>\n<blockquote>\n<p><a href=\"http:\/\/www.tylerhenry.com\/portfolio\/kinemetagraph\/\">Kinemetagraph<\/a> reflects the bodily movement of the visitor in real time with a matching pose from the history of Hollywood cinema. To achieve this, it correlates live motion capture data using Kinect-based \u201cskeleton tracking\u201d to an open-source computer vision research dataset of 20,000 Hollywood film stills with included character pose metadata for each image.<\/p>\n<\/blockquote>\n<p>The notable thing, I think, is that what required a dedicated hardware sensor a couple of years ago can now be done plug-in-free using just a browser and webcam. Progress!<\/p>\n<p><iframe loading=\"lazy\" src=\"https:\/\/player.vimeo.com\/video\/156356893?title=0&#038;portrait=0\" width=\"600\" height=\"338\" frameborder=\"0\" webkitallowfullscreen mozallowfullscreen allowfullscreen><\/iframe><\/p>\n<p><img decoding=\"async\" loading=\"lazy\" title=\"NewImage.png\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2018\/07\/NewImage-22.png\" alt=\"NewImage\" width=\"598\" height=\"295\" border=\"0\" \/><\/p>\n<p>[Via Paul Chang]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Apropos of Google\u2019s Move Mirror project (mentioned last week), here\u2019s a similar idea: Kinemetagraph reflects the bodily movement of the visitor in real time with a matching pose from the history of Hollywood cinema. To achieve this, it correlates live motion capture data using Kinect-based \u201cskeleton tracking\u201d to an open-source computer vision research dataset of [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[17,8],"tags":[],"_links":{"self":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/7217"}],"collection":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/comments?post=7217"}],"version-history":[{"count":4,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/7217\/revisions"}],"predecessor-version":[{"id":7221,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/7217\/revisions\/7221"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=7217"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=7217"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=7217"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}