Touchscreen Progress 4
The software is coming along nicely - I got the connected components algorithm working for blob detection (needs to be refined a little bit, but otherwise it's working well) and I also got what I think is a good algorithm for the blob ID tracking. Basically the algorithm is to figure out all the possible tagging scenarios given the current set of blobs on the screen and picks the one that would introduce the least total error (the smallest change from the last frame). It seems to work pretty well so far, but I've only tested it by tracking the lights in my house using my webcam.
I also got my LED's glued onto my screen. The UV glue ended up working fine in regular sunlight. Some internet sites warned against doing this but I had no problems. It took an hour or two to cure in partly cloudy weather. With a real UV lamp it should cure in under 30 seconds which would be pretty cool if I actually had one. Once I get them soldered up I can start doing some real tests.
6 Comments:
Nice work dude
David, I've uploaded this video taken from our prototype screen. Feel free to feed it through your budding software. (If OpenCV can't read it directly, I think Virtual Dub should be able to extract the image sequence.) You'll notice that I lick my fingers between motions to get a good FTIR-induced spot ;-)
Wow, thanks! I will try it with the video you sent. Looks like you are getting a nice clean result. Was that taken in the dark? Are you using any visible light filter?
OpenCV can load AVI's - it can also load static images (gif, jpeg, etc) and can capture from any WDM or VFW source so it should be able to do everything we need.
I should have my LED's glued to the acrylic and wired up today so I should be able to make some real tests soon.
That was taken in a dim (but not dark) room. To block out the visible light, I'm using an 880nm bandpass filter purchased from Newport Optical ($50). This filter is frequency matched to the frequency of my IR LEDs.
Are you using any filter at all? I've read about people fabricating "cheap and nasty" filters from 2 pieces of exposed film.
That would be me ;) I'll have to look into getting a bandpass filter like that. I bet that's a big help.
I had a play around last night
here are a few video i managed to shoot http://mrknow.info/?page_id=8
under random , straight and circle .
not sure if the quality id good enough i only had a few led's
Post a Comment
<< Home