No subject

ot enough sample images to compute the correct calibration.=A0 I'd sugg=
est gathering more images before hitting the 'calibrate' button.=A0=
 Try to get the checkerboard:<br>
<ul><li>filling the entire frame</li><li>very distant, in the four corners =
of the frame</li><li>both face-on and skewed for the above cases</li></ul>T=
hen hit &#39;calibrate&#39;.=A0 The gui uses a simple heuristic for when it=
 thinks it has enough calibration data, which seems to predict quite well f=
or the PR2&#39;s stereo cameras.=A0 It is likely that your custom setup is =
sufficiently different that the heuristic is being overly optimistic.<br>
<br>J<br><br><div class=3D"gmail_quote">On Mon, Oct 11, 2010 at 6:57 AM, Je=
ff Hyams <span dir=3D"ltr">&lt;<a href=3D"mailto:jeff.hyams at resquared.com">=
jeff.hyams at resquared.com</a>&gt;</span> wrote:<br><blockquote class=3D"gmai=
l_quote" style=3D"border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0p=
t 0pt 0.8ex; padding-left: 1ex;">
I am trying to run the camera_calibration to calibrate a simple custom setu=
p stereo pair.=A0 I am using the uvc_stereo package to publish the raw came=
ra images.<br><br>I get through the calibration (using a 5x4 checkerboard a=
t the moment) after a minute of moving the checkerboard to the various posi=
tions around the image.=A0 But once the calibrate button lights up and I hi=
t it, it seems to still be looking for the checkerboard.=A0 It also shows i=
mages which look to be zoomed in samples of the actual images, rather than =
what I would expect for poorly calibrated rectified images.=A0 It also seem=
s to be constantly recalculating the epipolar error (really high, usually o=
ver 10.0) whenever it finds the checkerboard after I have hit the calibrate=
 button, or reporting the checkerboard not found if it&#39;s not in the ima=
ge.<br>

<br>Based on the wiki page, I expected it to sample the images, then once t=
he button was hit, to calculate and then print out or save the results.=A0 =
Is this expected behavior, or am I doing something drastically wrong here?=
=A0 Am I just getting a really bad set of images for calibration that is sc=
rewing up the calculations?<br>

<br>I am only running the image_raw publisher(s).=A0 Do I need to also be r=
unning the stereo_image_proc while doing calibration?<br><br>Thanks,<br><fo=
nt color=3D"#888888"><br>Jeff Hyams<br>RE2, Inc.<br>
</font><br>_______________________________________________<br>
ros-users mailing list<br>
<a href=3D"mailto:ros-users at code.ros.org">ros-users at code.ros.org</a><br>
<a href=3D"https://code.ros.org/mailman/listinfo/ros-users" target=3D"_blan=
k">https://code.ros.org/mailman/listinfo/ros-users</a><br>
<br></blockquote></div><br><br clear=3D"all"><br>-- <br>J.<br><br>

--001636e90310b4ae25049259a8c8--