Hi<br>the potentiel of these accelerometer is great, but I need some help to really understand what can be done with them.<br>I mean for now i know openmoocow, gestures <br>What can I do with theses recognized gestures ? Load a command, call my mother ? I don't wnat to sound against their use, but for example, I prefer to take the fridge door with my hand and pull instead of yelling at the door "open !".<br>
For now, I miss some great examples. Some ideas :<br>* level ? (like with the air bubles to check the horizontality/verticality of devices)<br>* sport training : jogging<br>* wii - like video games remote controller <br>* some more ?.<br>
<br>By the way, I found this interested python scriptfrom thomas wood which read the accell values :<br><a href="http://blogs.gnome.org/thos/2008/07/01/openmoko-freerunner-test-application/">http://blogs.gnome.org/thos/2008/07/01/openmoko-freerunner-test-application/</a><br>
<br><div class="gmail_quote">2008/11/10 Paul V. Borza <span dir="ltr"><<a href="mailto:paul@accelsense.org">paul@accelsense.org</a>></span><br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Mickey,<br>
<br>
I've talked with Daniel recently and told him that I was working on<br>
recognizing contexts.<br>
For that I'm using self-organizing maps (Nokia is using these for<br>
gesture recognition) and I'll try to recognize walking, running,<br>
walking up/down stairs etc.<br>
Just wanted you to know that I'm continuing my work towards gestures,<br>
and walking patterns for the Neo :)<br>
<br>
This year I'm working on contexts like said before, but next year I'll<br>
try to merge hidden Markov models and self-organizing maps for gesture<br>
recognition.<br>
These SOM are amazing because you don't need to train them, it just<br>
adapts using unsupervised learning.<br>
I'm eager to see what will come out of it...<br>
<br>
Thanks,<br>
Paul<br>
<div class="Ih2E3d"><br>
On Mon, Nov 10, 2008 at 3:51 PM, Michael 'Mickey' Lauer<br>
<<a href="mailto:mickey@openmoko.org">mickey@openmoko.org</a>> wrote:<br>
</div><div><div></div><div class="Wj3C7c">> Am Monday 10 November 2008 14:14:45 schrieb Atilla Filiz:<br>
>> I don't know if there is any work towards this anyway, i think having an<br>
>> acc daemon like gpsd would be nice. The daemon can check for blocking in<br>
>> acc.meters and reset the hardware if necessary, and serve multiple<br>
>> clients(which is not very likely actually). This way maybe we can have more<br>
>> quality acc applications, if using them becomes easier and more stable.<br>
><br>
> We already have the amazing gesture recognition daemon by P.V.Borza which is<br>
> pending integration with the frameworkd. I think most applications will not<br>
> want to read the accellerometer data directly, but rather react to signals in<br>
> terms of gestures. Those (few) applications that do need direct access can<br>
> read from the input device nodes directly.<br>
><br>
> --<br>
> :M:<br>
><br>
> _______________________________________________<br>
> Openmoko community mailing list<br>
> <a href="mailto:community@lists.openmoko.org">community@lists.openmoko.org</a><br>
> <a href="http://lists.openmoko.org/mailman/listinfo/community" target="_blank">http://lists.openmoko.org/mailman/listinfo/community</a><br>
><br>
<br>
<br>
<br>
</div></div>--<br>
<font color="#888888">Paul V. Borza<br>
</font><div><div></div><div class="Wj3C7c"><br>
_______________________________________________<br>
Openmoko community mailing list<br>
<a href="mailto:community@lists.openmoko.org">community@lists.openmoko.org</a><br>
<a href="http://lists.openmoko.org/mailman/listinfo/community" target="_blank">http://lists.openmoko.org/mailman/listinfo/community</a><br>
</div></div></blockquote></div><br>