<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Pi-Tag &#8211; Matthew Petroff</title>
	<atom:link href="https://mpetroff.net/tag/pi-tag/feed/" rel="self" type="application/rss+xml" />
	<link>https://mpetroff.net</link>
	<description>mpetroff.net</description>
	<lastBuildDate>Sun, 30 Apr 2017 21:50:28 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	
	<item>
		<title>Pi-Tag Fiducial Marker Detector</title>
		<link>https://mpetroff.net/2017/04/pi-tag-fiducial-marker-detector/</link>
					<comments>https://mpetroff.net/2017/04/pi-tag-fiducial-marker-detector/#comments</comments>
		
		<dc:creator><![CDATA[Matthew Petroff]]></dc:creator>
		<pubDate>Sun, 30 Apr 2017 21:50:28 +0000</pubDate>
				<category><![CDATA[Programming]]></category>
		<category><![CDATA[computer vision]]></category>
		<category><![CDATA[fiducial]]></category>
		<category><![CDATA[marker]]></category>
		<category><![CDATA[Pi-Tag]]></category>
		<guid isPermaLink="false">https://mpetroff.net/?p=2442</guid>

					<description><![CDATA[Recently, I&#8217;ve been looking at various fiducial markers for computer vision applications. While some of these markers, such as AprilTags, have readily available reference implementations, others have no published code. While one of the markers I was looking at, Pi-Tags, &#8230; <a href="https://mpetroff.net/2017/04/pi-tag-fiducial-marker-detector/">Continue reading <span class="meta-nav">&#8594;</span></a>]]></description>
										<content:encoded><![CDATA[<p><span class="dropcap">R</span>ecently, I&#8217;ve been looking at various fiducial markers for computer vision applications. While some of these markers, such as <a href="https://april.eecs.umich.edu/software/apriltag.html">AprilTags</a>, have readily available reference implementations, others have no published code. While one of the markers I was looking at, <a href="http://www.dsi.unive.it/~atorsell/papers/Journals/MVA(24-6)2013.pdf">Pi-Tags</a>, does not have a reference implementation, it does have a third party implementation in the form of a <a href="http://www.ros.org/">Robot Operating System (ROS)</a> module, <a href="http://wiki.ros.org/cob_fiducials"><code>cob_fiducials</code></a>; this is great for robotics applications using ROS, but problematic otherwise. Since I wasn&#8217;t interested in using the detector with ROS, I separated it out into a <a href="https://github.com/mpetroff/pi-tag-detector">standalone library</a>. Additionally, I modified the detector to add a function that just returns the image pixel coordinates of the detected markers instead of calculating their poses, and added the ellipse refinement step<sup id="rf1-2442"><a href="https://mpetroff.net/2017/04/pi-tag-fiducial-marker-detector/#fn1-2442" title=" &lt;a href=&quot;https://doi.org/10.1007/s00138-008-0141-3&quot;&gt;Ouellet, Jean-Nicolas, and Patrick Hébert. &#8220;Precise ellipse estimation without contour point extraction.&#8221; Machine Vision and Applications 21, no. 1 (2009): 59.&lt;/a&gt; " rel="footnote">1</a></sup> that was mentioned in the Pi-Tag paper.<sup id="rf2-2442"><a href="https://mpetroff.net/2017/04/pi-tag-fiducial-marker-detector/#fn2-2442" title=" &lt;a href=&quot;https://doi.org/10.1007/s00138-012-0469-6&quot;&gt;Bergamasco, Filippo, Andrea Albarelli, and Andrea Torsello. &#8220;Pi-tag: a fast image-space marker design based on projective invariants.&#8221; Machine vision and applications 24, no. 6 (2013): 1295-1310.&lt;/a&gt; " rel="footnote">2</a></sup></p>
<p><a href="https://cdn0.mpetroff.net/wp-content/uploads/2017/04/pi-tag.jpg" title="Detected Pi-Tag" data-sbox="2442"><img decoding="async" class="aligncenter wp-image-2446 size-large" title="Detected Pi-Tag" src="https://cdn0.mpetroff.net/wp-content/uploads/2017/04/pi-tag-640x427.jpg" alt="Detected Pi-Tag" width="640" height="427" srcset="https://cdn0.mpetroff.net/wp-content/uploads/2017/04/pi-tag-640x427.jpg 640w, https://cdn0.mpetroff.net/wp-content/uploads/2017/04/pi-tag-300x200.jpg 300w, https://cdn0.mpetroff.net/wp-content/uploads/2017/04/pi-tag-1280x853.jpg 1280w, https://cdn0.mpetroff.net/wp-content/uploads/2017/04/pi-tag.jpg 1500w" sizes="(max-width: 640px) 100vw, 640px" /></a></p>
<hr class="footnotes"><ol class="footnotes" style="list-style-type:decimal"><li id="fn1-2442"><p > <a href="https://doi.org/10.1007/s00138-008-0141-3">Ouellet, Jean-Nicolas, and Patrick Hébert. &#8220;Precise ellipse estimation without contour point extraction.&#8221; Machine Vision and Applications 21, no. 1 (2009): 59.</a> &nbsp;<a href="https://mpetroff.net/2017/04/pi-tag-fiducial-marker-detector/#rf1-2442" class="backlink" title="Return to footnote 1.">&#8617;</a></p></li><li id="fn2-2442"><p > <a href="https://doi.org/10.1007/s00138-012-0469-6">Bergamasco, Filippo, Andrea Albarelli, and Andrea Torsello. &#8220;Pi-tag: a fast image-space marker design based on projective invariants.&#8221; Machine vision and applications 24, no. 6 (2013): 1295-1310.</a> &nbsp;<a href="https://mpetroff.net/2017/04/pi-tag-fiducial-marker-detector/#rf2-2442" class="backlink" title="Return to footnote 2.">&#8617;</a></p></li></ol>]]></content:encoded>
					
					<wfw:commentRss>https://mpetroff.net/2017/04/pi-tag-fiducial-marker-detector/feed/</wfw:commentRss>
			<slash:comments>6</slash:comments>
		
		
			</item>
	</channel>
</rss>

<!--
Performance optimized by W3 Total Cache. Learn more: https://www.boldgrid.com/w3-total-cache/?utm_source=w3tc&utm_medium=footer_comment&utm_campaign=free_plugin

Page Caching using Disk: Enhanced 
Content Delivery Network via Amazon Web Services: CloudFront: cdn0.mpetroff.net
Minified using Disk

Served from: mpetroff.net @ 2026-03-31 01:40:00 by W3 Total Cache
-->