<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>OpenCV on WANG Zhaofeng · Course Portfolio</title><link>https://zzefone.github.io/myblog/tags/opencv/</link><description>Recent content in OpenCV on WANG Zhaofeng · Course Portfolio</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 19 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://zzefone.github.io/myblog/tags/opencv/index.xml" rel="self" type="application/rss+xml"/><item><title>Planar AR: matching a marker and replacing it</title><link>https://zzefone.github.io/myblog/posts/bcv-marker-based-ar/</link><pubDate>Sat, 17 Oct 2026 00:00:00 +0000</pubDate><guid>https://zzefone.github.io/myblog/posts/bcv-marker-based-ar/</guid><description>&lt;p&gt;A reference image, a camera frame and a replacement image. The BCV final project is to find the first image in the frame and put the replacement in the same position. I tested the code on generated scenes, then on the marker displayed on a phone in front of the integrated webcam.&lt;/p&gt;&#10;&lt;h2 id="the-matching-pipeline"&gt;&#10; The matching pipeline&#10; &lt;a class="heading-link" href="#the-matching-pipeline"&gt;&#10; &lt;i class="fa-solid fa-link" aria-hidden="true" title="Link to heading"&gt;&lt;/i&gt;&#10; &lt;span class="sr-only"&gt;Link to heading&lt;/span&gt;&#10; &lt;/a&gt;&#10;&lt;/h2&gt;&#10;&lt;p&gt;SIFT is the default, with ORB available in the GUI. Both use brute-force kNN matching with two neighbours. A ratio test removes ambiguous matches, and RANSAC estimates the homography from the remaining pairs.&lt;/p&gt;</description></item></channel></rss>