<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Latest YOLO Pose Estimation Demo]]></title><description><![CDATA[<p>Dear All,<br /></p>
<p>I wanted to share the latest version of my YOLO-based pose estimation and masking patches, now using the YOLO26 models from Ultralytics.</p>
<p>This version requires Isadora 4.5.0 and a bit of initial setup to install the necessary Python libraries and download the YOLO models. The included HTML guide will walk you through the process.</p>
<p>I've included two pose estimation examples: one that lets you switch between a prerecorded movie and a live camera, and a simpler version designed exclusively for live camera input.</p>
<p>Both examples visualize the tracked body points, but you can also use the individual X/Y coordinates directly in your own patches to control whatever you like.<br /></p>
<p>I don't have an NVIDIA-based Windows PC to test with, but everything works quite well on my older M1 Mac. If you can try this on a Windows machine with an NVIDIA GPU and offer some feedback, that would be great!</p>
<p>To begin, open <strong>READ_ME_YOLO_Pose_Estimation_and_Masking.html</strong> and follow the instructions within.<br /><br />You can <a href="https://troikatronix.com/files/yolo-pose-estimation-v4.5.0.zip">download the files here</a>.</p>
<p>Happy Tracking!<br />Mark</p>
<p><img src="/assets/uploads/files/1794924940320-isadoratemp26111715152601.jpg" style="cursor:pointer" /></p>]]></description><link>https://community.troikatronix.com/topic/9529/latest-yolo-pose-estimation-demo</link><generator>RSS for Node</generator><lastBuildDate>Tue, 17 Nov 2026 15:33:10 GMT</lastBuildDate><atom:link href="https://community.troikatronix.com/topic/9529.rss" rel="self" type="application/rss+xml"/><pubDate>Tue, 17 Nov 2026 14:18:42 GMT</pubDate><ttl>60</ttl></channel></rss>