Calling Any Java Programmers - Computer Vision Project - Page 4

pronerd · 05-07-2006, 01:25 PM

Of the people that have this working have any of you done it on Linux?

sama · 05-07-2006, 03:13 PM

hey there

try this jmf download for linux. I've never tried it on there, but that's the only part that needs to be working. once you have a capture device working with the JMF, this code should work failry easily.

I'll help what I can. have u got the JMF installed?

Genesisfactor · 05-13-2006, 06:41 AM

wow, sad thing was, if i wsan't in that car accident, i'd be taking a class on this right now, have just finished my final, and may be able to help you guys out tremendously. I'm so useless now....

Ah well, have you guys done any stereo vision projects yet? When you get it to see in 3D...

Impressive though. I'll be subscribing to this thread as i won't have too much to say other than testing out stuff and griping wihen it doesn't go right. I'm just good like that

I do have a lego mindstorms Vision Command CD, which can track certian colors if you want it too. From the posts, i can't see what was introduced, and i can do logic right now, so reading code is out for me.

sama · 05-13-2006, 07:13 AM

heh, lego mindstorms! I'm currently modifying some code I wrote for that serial port to work with java. I'm porting it over so I can get java to talk to my car's ibus.

even this imaging code comes from that lego projct I did a few years back.

I've put this vision project on hold for a short period, whilst I get my head around optic flow... amongst the 6 billion other projects I want to do

Genesisfactor · 05-16-2006, 09:29 AM

LOL, nice sama. that reminds me, my old robotics professor was doing a post doctorate research on robot vision i should drop him an email!

Genesisfactor · 05-22-2006, 09:22 AM

no updates?

sama · 05-22-2006, 09:25 AM

unfortunately I've put this project on hold for a bit. I'm currently working on tomtom (pretty much done) and on a new ibus program 'cos I'm getting very annoyed with what I can't do in vb!

I haven't forgotten this, I will resume at some point. I wish I didn't have to go to work!

Lo5t · 12-23-2007, 06:29 AM

ah this is so cool. I have been looking all over the place for people doing this kind of stuff and in java too. although i never considered this general appoach for object recognition. i was trying to develope a approch based more on 3d. but this stuff is so cool.

Genesisfactor · 12-23-2007, 07:50 AM

im feeling a little brave with my C++ knowledge. i will join this task force. Sama, ill im you Merry christmas!

JC-S60 · 12-23-2007, 08:52 AM

Quote: Originally Posted by sama

this is exactly my aim, to try to get a framework going so that people with little or no knowledge of vision algorithms can build applications, which in turn would drive the development of algorithm plugins to use.

my maths isn't the best either, but there are plenty of resources out there.

the current download offers a fairly simple motion detection algorithm. it learns the background by continously averaging pixel values over time. It detects foreground objects by subtracting the current frame from the learnt background.

the problems currently with it are that any major change in lighting will render the background model useless, since it no longer applies to the new lighting conditions. a way of detecting this would be useful, so a reset can be issued to the background learning loop. This infers that there would be a window where the foreground is not determined whilst the background is being learnt again.

Perhaps another motion detection algorithm can kick in at that stage, something like differential analysis (subtracting previous frame from current). hopefully, by using knowledge prior to the light change, the regions of last known moving objects can be applied to the differntial algorithm.

Im' thinking out loud here on how the impact of lighting changes can be minimised. you may need to study the code a little to to see what I'm gettin at.

Perhaps using the background + a variable that represents intensity of the whole image. This way you can learn the background and keep it if all pixels change in the same way (intensity of whole image changes)... don't know if that's possible but it would be the most logical way of doing this.
On the other hand, it will only work within a certain dynamical range, as long as everything in the backgound remains visible (distinguishable pixels).

Good luck with this project!

Joachim

Maheriano · 02-15-2008, 12:36 PM

Very interesting project, wanted to bring it out of hibernation after finding it on Google.
Any updates? I'm using the JMF myself to develop a new front end but won't be incorporating video streaming until all the audio is done.

mc1392 · 03-18-2008, 08:46 AM

Hi,

Im very interested in your project.
What's available?

M