{"id":9136,"date":"2019-08-20T10:51:34","date_gmt":"2019-08-20T17:51:34","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=9136"},"modified":"2019-08-20T10:54:58","modified_gmt":"2019-08-20T17:54:58","slug":"give-yourself-a-hand-realtime-3d-hand-tracking-for-your-projects","status":"publish","type":"post","link":"https:\/\/jnack.com\/blog\/2019\/08\/20\/give-yourself-a-hand-realtime-3d-hand-tracking-for-your-projects\/","title":{"rendered":"Give yourself a hand! Realtime 3D hand-tracking for your projects"},"content":{"rendered":"<p>\u201cWhy doesn\u2019t it recognize The Finger?!\u201d asks my indignant, mischievous 10-year-old Henry, who with his brother has offered to donate a rich set of training data. &#x1f643;<\/p>\n<p>Juvenile amusement notwithstanding, I\u2019m delighted that my teammates have released a <a href=\"https:\/\/ai.googleblog.com\/2019\/08\/on-device-real-time-hand-tracking-with.html\">badass hand-tracking model<\/a>, especially handy (oh boy) for use with MediaPipe (see <a href=\"http:\/\/jnack.com\/blog\/2019\/06\/20\/ml-developers-come-check-out-mediapipe\/\">previous<\/a>), our open-source pipeline for building ML projects.<\/p>\n<p><center><img decoding=\"async\" src=\"https:\/\/1.bp.blogspot.com\/-H71UdvAObkQ\/XVrSxUc2rFI\/AAAAAAAAEhU\/h7NuEZ23Pu4XAdwCcaKNxakGbN4nJUc2wCLcBGAs\/s400\/image2.gif\"><\/center><\/p>\n<blockquote><p>Today we are announcing the release of a new approach to hand perception, which we previewed&nbsp;CVPR 2019&nbsp;in June, implemented in&nbsp;<a href=\"http:\/\/mediapipe.dev\/\">MediaPipe<\/a>\u2014an open source cross platform framework for building pipelines to process perceptual data of different modalities, such as video and audio. This approach provides high-fidelity hand and finger tracking by employing machine learning (ML) to infer 21 3D keypoints of a hand from just a single frame. Whereas current state-of-the-art approaches rely primarily on powerful desktop environments for inference, our method achieves real-time performance on a mobile phone, and even scales to multiple hands. We hope that&nbsp;providing this hand perception functionality&nbsp;to the wider research and development community will result in an emergence of creative use cases, stimulating new applications and new research avenues.<\/p><\/blockquote>\n<p>&#x1f64c;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u201cWhy doesn\u2019t it recognize The Finger?!\u201d asks my indignant, mischievous 10-year-old Henry, who with his brother has offered to donate a rich set of training data. &#x1f643; Juvenile amusement notwithstanding, I\u2019m delighted that my teammates have released a badass hand-tracking model, especially handy (oh boy) for use with MediaPipe (see previous), our open-source pipeline for [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[13],"tags":[],"_links":{"self":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/9136"}],"collection":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/comments?post=9136"}],"version-history":[{"count":4,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/9136\/revisions"}],"predecessor-version":[{"id":9140,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/9136\/revisions\/9140"}],"wp:attachment":[{"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=9136"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=9136"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=9136"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}