TiagoTiago
Joined: 20 Jan 2007 Posts: 710 Location: Brasil
Digg It |
Posted: Thu Jun 21, 2007 10:01 pm Post subject: |
|
|
depending on the type of motion (like spinning the wiimote for the lasso) an obvious pattern will be produced on the acceleration data over time, depending on which language and stuff you will be using to write your gesture recognition algorithm, this kind of motions would be easilly detectable, but acquiring relative positioning and short motions would be harder due to the nature of the way acceleration is measured (cause of seemingly random bouncing, minimum velocity detectable, speed and time resolution, dealing with those distortions you mentioned and probably a bunch of other stuff), it isn't impossible, just very hard to achieve, and not many people have managed to do this so far (and I don't think anyone has released a free library or ope-source code for it yet (although I've heard of free generic gesture recognition systems producing some interesting results, but I think nothing major so far )
edit: someone seems to be making some siginificant advances ont his are, read down the last page http://www.wiili.org/forum/glovepie-alternative-t2160-s56.html _________________ please put the scripts on the wiki so they dont get lost as new stuff is posted!
phpBB doesnt like me,somtimes it will forget to warn me about new replies to threads I asked it to,if you see a thread I should have responded, could please email me? |
|