Head tracking in room

This is for discussion and development of non-commercial open source VR/AR projects (e.g. Kickstarter applicable, etc). Contact MTBS admins at customerservice@mtbs3d.com if you are unsure if your efforts qualify.
Post Reply
MemeBox
Two Eyed Hopeful
Posts: 55
Joined: Sat Sep 01, 2012 9:23 am

Head tracking in room

Post by MemeBox »

I've been mulling over how to do absolute position tracking in 3d space, in a room sized area. I've come up with an idea, I'm wondering if anyone has done it before (on this forum) and if I am re-inventing the wheel...

I'm thinking about placing web cameras around a room and then calculating the position and rotation of those cameras and then using blob tracking to track an IR LED. I know this has been done elsewhere on this forum, but has anyone done the full camera calibration setup?

I'm thinking of using VisualSFM: http://www.cs.washington.edu/homes/ccwu/vsfm/

This allows you to work out the camera parameters (focal length, radial distortion) and the position of each camera. It seems to work pretty well. From this you can work out the 3d position of a blob by combining the x,y location in each camera, using the fundamental matrix and the position...

Has anyone done this? Do you have any notes to help me through?

Many thanks :)
User avatar
brantlew
Petrif-Eyed
Posts: 2221
Joined: Sat Sep 17, 2011 9:23 pm
Location: Menlo Park, CA

Re: Head tracking in room

Post by brantlew »

If you just want simple IR tracking, the Wiimote is an excellent place to start. It will handle all the blob detection / processing for you and convert the data into ready-to-use point coordinates (limited to 4 points). I have worked with Wiimote IR tracking a lot and it is adequate for this task. Here's a setup I envisioned a while ago but never implemented. Also the entire thread is a good read and is chock-full of ideas for 6DOF tracking.

http://www.mtbs3d.com/phpBB/viewtopic.p ... 120#p77575
Post Reply

Return to “VR/AR Research & Development”