I had missed this in my email, don&#39;t know where you are yet.  eblearn looks cool but all these things have limits that work well on certain classes of problems and not others (that is in fact a consequence of the &quot;no free lunch theorem&quot;).  I sort of like FLANN because it is easy to scale over clusters, easy to load local models, is inherently incremental and on a give machine it scales logarithmically in the number of objects learned. The user&#39;s job would then be not to find &quot;good&quot; features but features that work well with FLANN. <div>
<br></div><div>For the solutions in perception challenge. I had thought about not requiring people to use ROS.  My next thought was: &quot;Let&#39;s require people to use ROS or else they are free not to join&quot;.  The reason is, someone else is providing and maintaining a rich framework ROS and it&#39;s uniform so that someone can compare their new algorithms against old ones without changing API etc.  It&#39;s also nice in that once you write code for the contest, the exact same code can be used to grab objects using a real robot or the robot simulator. A lot of things like that come for free on ROS including dynamic settings of parameters etc.</div>
<div><br></div><div>One difference that you might think of is that I don&#39;t want to just identify an object, I want to know its pose relative to the camera.</div><div><br></div><div>Gary<br><br><div class="gmail_quote">
On Tue, Nov 23, 2010 at 3:06 PM, Pierre S <span dir="ltr">&lt;<a href="mailto:pierre.sermanet@gmail.com">pierre.sermanet@gmail.com</a>&gt;</span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<div class="gmail_quote"><div class="im"><div><br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<br>
All and all eblearn + visiongrader seem like great tools, with a nice<br>
and well thought API.<br>
I will definitely look more in detail about their internals (I already<br>
had played around with eblearn a few months ago) and use/re-use as<br>
much as possible the existing code base.<br>
<br></blockquote><div><br></div></div><div>Thanks for your interest Rodrigo. If you reuse existing parts, I guess the best for what you want to do would be to use the tensor library libidx and its GUI as a basis for image/matrix manipulations (not tied to any learning scheme) and visiongrader for performance evaluation.</div>


<div><br></div><font color="#888888"><div>Pierre</div></font></div>
<br>_______________________________________________<br>
ros-users mailing list<br>
<a href="mailto:ros-users@code.ros.org">ros-users@code.ros.org</a><br>
<a href="https://code.ros.org/mailman/listinfo/ros-users" target="_blank">https://code.ros.org/mailman/listinfo/ros-users</a><br>
<br></blockquote></div><br></div>