{"id":170652,"date":"2011-01-25T09:18:30","date_gmt":"2011-01-25T09:18:30","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/project\/human-pose-estimation-for-kinect\/"},"modified":"2022-09-07T10:53:34","modified_gmt":"2022-09-07T17:53:34","slug":"human-pose-estimation-for-kinect","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/human-pose-estimation-for-kinect\/","title":{"rendered":"Human Pose Estimation for Kinect"},"content":{"rendered":"<p class=\"asset-content\"><img loading=\"lazy\" decoding=\"async\" class=\"alignleft\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/02\/human-pose-estimation-for-kinect-2.jpg\" alt=\"\" width=\"72\" height=\"72\" \/>Kinect for Xbox 360 and Windows makes you the controller by fusing 3D imaging hardware with markerless human-motion capture software. Our group investigates such software. Mixing computer vision, graphics, and machine learning techniques, we look at how to build algorithms that can learn to recognize human poses quickly and reliably.<\/p>\n<p><!-- .asset-content --><\/p>\n<div id=\"en-usprojectsvrkinectdefault\" class=\"page-content\">\n<h1>Images<\/h1>\n<table style=\"height: 583px;\" width=\"655\">\n<tbody>\n<tr>\n<td>\n<p><span id=\"f7a51335-bd10-4f4d-87f7-a3c09a2b0923\" class=\"ImageBlock fn\"><img decoding=\"async\" id=\"Imagef7a51335-bd10-4f4d-87f7-a3c09a2b0923\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/02\/vrkinect-standard_view.jpg\" alt=\"\" \/><span id=\"ImageCaptionf7a51335-bd10-4f4d-87f7-a3c09a2b0923\" class=\"ImageCaptionCoreCss ImageCaption\"><\/span><\/span><\/p>\n<p><span id=\"f7a51335-bd10-4f4d-87f7-a3c09a2b0923\" class=\"ImageBlock fn\"><span id=\"ImageCaptionf7a51335-bd10-4f4d-87f7-a3c09a2b0923\" class=\"ImageCaptionCoreCss ImageCaption\">Traditional RGB image<\/span><\/span><\/td>\n<td>\n<p><span id=\"3f47deae-b757-4d4e-8fe4-a46674455c79\" class=\"ImageBlock fn\"><img decoding=\"async\" id=\"Image3f47deae-b757-4d4e-8fe4-a46674455c79\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/02\/vrkinect-rgb_view.jpg\" alt=\"\" \/><span id=\"ImageCaption3f47deae-b757-4d4e-8fe4-a46674455c79\" class=\"ImageCaptionCoreCss ImageCaption\"><\/span><\/span><\/p>\n<p><span id=\"3f47deae-b757-4d4e-8fe4-a46674455c79\" class=\"ImageBlock fn\"><span id=\"ImageCaption3f47deae-b757-4d4e-8fe4-a46674455c79\" class=\"ImageCaptionCoreCss ImageCaption\">Image from new depth sensing camera<\/span><\/span><\/td>\n<\/tr>\n<tr>\n<td>\n<p><span id=\"830cb271-97ea-4127-a56b-7c1fbea9aeb8\" class=\"ImageBlock fn\"><img decoding=\"async\" id=\"Image830cb271-97ea-4127-a56b-7c1fbea9aeb8\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/02\/vrkinect-harlequin_view.jpg\" alt=\"\" \/><span id=\"ImageCaption830cb271-97ea-4127-a56b-7c1fbea9aeb8\" class=\"ImageCaptionCoreCss ImageCaption\"><\/span><\/span><\/p>\n<p><span id=\"830cb271-97ea-4127-a56b-7c1fbea9aeb8\" class=\"ImageBlock fn\"><span id=\"ImageCaption830cb271-97ea-4127-a56b-7c1fbea9aeb8\" class=\"ImageCaptionCoreCss ImageCaption\">Body parts inferred by our recognition algorithm<\/span><\/span><\/td>\n<td>\n<p><span id=\"2c512f24-4c40-4714-bcc1-cf05318ce515\" class=\"ImageBlock fn\"><img decoding=\"async\" id=\"Image2c512f24-4c40-4714-bcc1-cf05318ce515\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/02\/vrkinect-position_view.jpg\" alt=\"\" \/><span id=\"ImageCaption2c512f24-4c40-4714-bcc1-cf05318ce515\" class=\"ImageCaptionCoreCss ImageCaption\"><\/span><\/span><\/p>\n<p><span id=\"2c512f24-4c40-4714-bcc1-cf05318ce515\" class=\"ImageBlock fn\"><span id=\"ImageCaption2c512f24-4c40-4714-bcc1-cf05318ce515\" class=\"ImageCaptionCoreCss ImageCaption\">3D body part position proposals<\/span><\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n<div id=\"en-usprojectsvrkinectdefault\" class=\"page-content\">\n<h3>Related Press<\/h3>\n<ul>\n<li><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"http:\/\/www.scientificamerican.com\/article.cfm?id=microsoft-project-natal\">Binary Body Double: Microsoft Reveals the Science Behind Project Natal for Xbox 360<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><br \/>\n<b>Scientific American<\/b><\/li>\n<li><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"http:\/\/www.wired.co.uk\/magazine\/archive\/2010\/11\/features\/the-game-changer\">Kinect for Xbox 360: The inside story of Microsoft&#8217;s secret &#8216;Project Natal&#8217;<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><br \/>\n<b>WIRED UK<\/b><\/li>\n<li><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"http:\/\/blogs.wsj.com\/tech-europe\/2010\/11\/08\/key-kinect-technology-devised-in-cambridge-lab\/\">Key Kinect Technology Devised in Cambridge Lab<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><br \/>\n<b>Wall St Journal Europe<\/b><\/li>\n<\/ul>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Kinect for Xbox 360 and Windows makes you the controller by fusing 3D imaging hardware with markerless human-motion capture software. Our group investigates such software. Mixing computer vision, graphics, and machine learning techniques, we look at how to build algorithms that can learn to recognize human poses quickly and reliably. Images Traditional RGB image Image [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556,13562,13551,13554],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-170652","msr-project","type-msr-project","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-computer-vision","msr-research-area-graphics-and-multimedia","msr-research-area-human-computer-interaction","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"2011-01-25","related-publications":[164368,164375,153413,158763,158765,160722,160924,161784,162557,162558,163767],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Antonio Criminisi","user_id":41790,"people_section":"Section name 0","alias":"acriminisi"}],"msr_research_lab":[],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/170652"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/170652\/revisions"}],"predecessor-version":[{"id":875988,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/170652\/revisions\/875988"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=170652"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=170652"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=170652"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=170652"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=170652"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}