We closed this forum 18 June 2010. It has served us well since 2005 as the ALPHA forum did before it from 2002 to 2005. New discussions are ongoing at the new URL http://forum.processing.org. You'll need to sign up and get a new user account. We're sorry about that inconvenience, but we think it's better in the long run. The content on this forum will remain online.
Page Index Toggle Pages: 1
optical flow eyeballs (Read 1077 times)
optical flow eyeballs
May 23rd, 2009, 10:38pm
 
Hey all, just a quick query,
                                         I'm working on a project now that involves optical flow and motion tracking, there's a layered graphic with multiple instances of eyeball images that I have to track for them to follow the direction of movement in a captured image. I thought that using optical flow would be the best solution for something like this, but I need to create an irregular grid for the tracking, constrain them to the area of the eyeballs themselves, and then bound them inside the radius of the image of the eyeball, anything I should keep in mind doing this? What would be the best method of doing it?
Re: optical flow eyeballs
Reply #1 - Jul 27th, 2009, 5:41am
 
Hi there,

I have worked on a very similar project in the past.

...

My project involved eyeballs being projected on a semi-transparent foil onto shop windows. Since the webcam responsible for motion tracking was looking at the projected image, I needed to create 'ignore areas' for the webcam input.

I have used the JMyron library for blob detection, so no optical flow was used. The JMyron library was ideal for me since I could capture webcam, modify the webcam image to create 'ignore areas', and then derive physical locations of people walking in front of the installation through the blob detection supplied by the library.

For an example, check the video of this installation.
You can also see photo's of different results.

Feel free to contact me if you have questions.
Page Index Toggle Pages: 1