<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en-gb">
<link rel="self" type="application/atom+xml" href="http://theeyetribe.com/forum/feed.php?f=9&amp;t=34" />

<title>The Eye Tribe</title>
<subtitle>Developer Forum</subtitle>
<link href="http://theeyetribe.com/forum/index.php" />
<updated>2014-01-21T04:06:55+02:00</updated>

<author><name><![CDATA[The Eye Tribe]]></name></author>
<id>http://theeyetribe.com/forum/feed.php?f=9&amp;t=34</id>
<entry>
<author><name><![CDATA[ikeda@sys.es.osaka-u.ac.jp]]></name></author>
<updated>2014-01-21T04:06:55+02:00</updated>
<published>2014-01-21T04:06:55+02:00</published>
<id>http://theeyetribe.com/forum/viewtopic.php?t=34&amp;p=167#p167</id>
<link href="http://theeyetribe.com/forum/viewtopic.php?t=34&amp;p=167#p167"/>
<title type="html"><![CDATA[Re: Unit of PupilSize]]></title>

<content type="html" xml:base="http://theeyetribe.com/forum/viewtopic.php?t=34&amp;p=167#p167"><![CDATA[
Hi,<br /><br />Thank you for the quick reply. I understand it. <br /><br />Of course, I'd prefer output both absolute and normalized. <br />At least, I hope to get some conversion parameters to the PupilCenter's dimension.<br /><br />ikeda<p>Statistics: Posted by <a href="http://theeyetribe.com/forum/memberlist.php?mode=viewprofile&amp;u=760">skataikeda@sys.es.osaka-u.ac.jp</a> — 21 Jan 2014, 04:06</p><hr />
]]></content>
</entry>
<entry>
<author><name><![CDATA[Martin]]></name></author>
<updated>2014-01-16T15:15:00+02:00</updated>
<published>2014-01-16T15:15:00+02:00</published>
<id>http://theeyetribe.com/forum/viewtopic.php?t=34&amp;p=129#p129</id>
<link href="http://theeyetribe.com/forum/viewtopic.php?t=34&amp;p=129#p129"/>
<title type="html"><![CDATA[Re: Unit of PupilSize]]></title>

<content type="html" xml:base="http://theeyetribe.com/forum/viewtopic.php?t=34&amp;p=129#p129"><![CDATA[
Hi Ikeda,<br /><br />The PupilSize right now is a <span style="font-style: italic">relative</span> value that is not calibrated to a physical dimension. You can use it to see if the pupil dilates or contracts and by how much compared to the original state. <br /><br />The PupilCenter is output in normalized coordinates 0 to 1. This is because using sensor pixel values would require knowing resolution of the sensor to compute the location. Normalized coordinates makes it easier to draw a trackbox and mapping coordinates. <br /><br />We have considered using normalized coordinates for the estimated on-screen gaze coordinates as well but that makes it more difficult for developers since most programming relies on screen pixels. It would be cumbersome to fetch the screen resolution and convert coordinates for every sample. We could of course output both absolute and normalized, would you prefer?<br /><br />A upcoming release scheduled for February will output pupil size in absolute value, with a <span style="font-style: italic">millimeter</span> resolution.<p>Statistics: Posted by <a href="http://theeyetribe.com/forum/memberlist.php?mode=viewprofile&amp;u=117">skataMartin</a> — 16 Jan 2014, 15:15</p><hr />
]]></content>
</entry>
<entry>
<author><name><![CDATA[ikeda@sys.es.osaka-u.ac.jp]]></name></author>
<updated>2014-01-16T11:15:28+02:00</updated>
<published>2014-01-16T11:15:28+02:00</published>
<id>http://theeyetribe.com/forum/viewtopic.php?t=34&amp;p=126#p126</id>
<link href="http://theeyetribe.com/forum/viewtopic.php?t=34&amp;p=126#p126"/>
<title type="html"><![CDATA[[Resolved] Unit of PupilSize]]></title>

<content type="html" xml:base="http://theeyetribe.com/forum/viewtopic.php?t=34&amp;p=126#p126"><![CDATA[
If I may ask a quite technical question here,<br />could you tell me what the unit of PupilSize actually is?<br /><br />I think the unit of PupilSize is not the same as <br />that of either PupilCenterCoordinates or RawCoordinates<br />because I tried to WriteLine the actual values <br />with the following code in GazeDot::OnGazeUpdate().<br /><br /><dl class="codebox"><dt>Code: </dt><dd><code>    System.Console.WriteLine(&quot;{0} {1} {2} {3} {4}&quot;,<br />        gazeData.LeftEye.PupilSize, gazeData.RightEye.PupilSize,<br /><br />        //Pupil Distance<br />        gazeData.RightEye.PupilCenterCoordinates.X - gazeData.LeftEye.PupilCenterCoordinates.X,<br />        gazeData.RightEye.SmoothedCoordinates.X    - gazeData.LeftEye.SmoothedCoordinates.X,<br />        gazeData.RightEye.RawCoordinates.X         - gazeData.LeftEye.RawCoordinates.X<br />        );<br /></code></dd></dl><br /><br />An example line of the output is like this.<br />The two pupil sizes are written in a clearly different scale from the other ones.<br /><br />&gt; 22.993221282959 22.993221282959 0.169162213802338 6.513671875 -7.025146484375<br /><br />In GazeEye.cs, I found the following comments, <br />which probably mean the unit of pupil size is the same as that of pupil center.<br /><br /><dl class="codebox"><dt>Code: </dt><dd><code>        /// &lt;summary&gt;<br />        /// Pupil center coordinates in normalized values<br />        /// &lt;/summary&gt;<br />        &#91;JsonProperty(PropertyName = Protocol.FRAME_PUPIL_CENTER)&#93;<br />        public Point2D PupilCenterCoordinates { get; set; }<br /><br />        /// &lt;summary&gt;<br />        /// Pupil size in normalized value<br />        /// &lt;/summary&gt;<br />        &#91;JsonProperty(PropertyName = Protocol.FRAME_PUPIL_SIZE)&#93;<br />        public double PupilSize { get; set; }<br /></code></dd></dl><br /><br />On the other hand, I found another description about pupil size <br />in the tutorial page <a href="http://dev.theeyetribe.com/tutorial/" class="postlink">http://dev.theeyetribe.com/tutorial/</a>.<br />This means pupil size is represented by the on-screen unit.<br /><br /><blockquote class="uncited"><div><br />... where the OnGazeUpdate is of most interest since it contains the coordinates of <br />the estimated on-screen gaze position, size of the pupils, position relative to the sensor etc.<br /></div></blockquote><br /><br />Do you know the actual unit of pupil size or how to calibrate it?<p>Statistics: Posted by <a href="http://theeyetribe.com/forum/memberlist.php?mode=viewprofile&amp;u=760">skataikeda@sys.es.osaka-u.ac.jp</a> — 16 Jan 2014, 11:15</p><hr />
]]></content>
</entry>
</feed>