<?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>Perpetual Student &#187; cool</title>
	<atom:link href="http://perpetualstudent.net/blog/tag/cool/feed/" rel="self" type="application/rss+xml" />
	<link>http://perpetualstudent.net/blog</link>
	<description>Just another student of the web</description>
	<lastBuildDate>Fri, 20 Jan 2012 03:20:07 +0000</lastBuildDate>
	<language>en</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.2.1</generator>
		<item>
		<title>Researchers reconstruct 3D models of a city from tourist photos</title>
		<link>http://perpetualstudent.net/blog/2009/09/30/researchers-reconstruct-3d-models-of-a-city-from-tourist-photos/</link>
		<comments>http://perpetualstudent.net/blog/2009/09/30/researchers-reconstruct-3d-models-of-a-city-from-tourist-photos/#comments</comments>
		<pubDate>Wed, 30 Sep 2009 14:00:44 +0000</pubDate>
		<dc:creator>Michael Thaler</dc:creator>
				<category><![CDATA[research]]></category>
		<category><![CDATA[3D]]></category>
		<category><![CDATA[advancement]]></category>
		<category><![CDATA[cool]]></category>
		<category><![CDATA[technology]]></category>
		<category><![CDATA[video]]></category>

		<guid isPermaLink="false">http://perpetualstudent.net/blog/?p=18</guid>
		<description><![CDATA[As a quick early indicator of the sort of results analyzing the Internet can produce, a group of researchers at the University of Washington tried an experiment: reconstruct cities from nothing but images from an Internet search. They succeeded at creating models of landmarks in Rome and Venice, and the entire Old City of Dubrovnik. [...]]]></description>
			<content:encoded><![CDATA[<p>As a quick early indicator of the sort of results analyzing the Internet can produce, a <a href="http://grail.cs.washington.edu/rome/">group of researchers at the University of Washington</a> tried an experiment: reconstruct cities from nothing but images from an Internet search. They succeeded at creating models of landmarks in Rome and Venice, and the entire Old City of Dubrovnik.</p>
<p>To do this, they used a cluster of machines working in parallel to match common data points in pictures taken by tourists matching a search. Their largest work, Dubrovnik, was completed in 17.5 hours.</p>
<p><object width="570" height="344"><param name="movie" value="http://www.youtube.com/v/sQegEro5Bfo&#038;rel=0&#038;color1=0xb1b1b1&#038;color2=0xcfcfcf&#038;hl=en&#038;feature=player_embedded&#038;fs=1"></param><param name="allowFullScreen" value="true"></param><param name="allowScriptAccess" value="always"></param><embed src="http://www.youtube.com/v/sQegEro5Bfo&#038;rel=0&#038;color1=0xb1b1b1&#038;color2=0xcfcfcf&#038;hl=en&#038;feature=player_embedded&#038;fs=1" type="application/x-shockwave-flash" allowfullscreen="true" allowScriptAccess="always" width="570" height="344"></embed></object></p>
<p>This bears repetition: this was done with nothing but a search on user-submitted photos from Flickr and raw computing power. In other words, they distilled images taken by numerous, disconnected people into a single common conglomeration of what they all recorded, automatically determining what matched what in all the photos.</p>
<p>This is incredible research, and it&#8217;s an excellent microcosm of how the Internet&#8217;s data can be crystallized into something more than the sum of its parts.</p>
]]></content:encoded>
			<wfw:commentRss>http://perpetualstudent.net/blog/2009/09/30/researchers-reconstruct-3d-models-of-a-city-from-tourist-photos/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
	</channel>
</rss>

