Attention: Answers.ros.org is deprecated as of August the 11th, 2023. Please visit robotics.stackexchange.com to ask a new question. This site will remain online in read-only mode during the transition and into the foreseeable future. Selected questions and answers have been migrated, and redirects have been put in place to direct users to the corresponding questions on Robotics Stack Exchange. Additional details are available here.

Can openni_tracker calibration be avoided for successive users?

asked 2011-04-16 12:53:10 -0500

Pi Robot
4046 ●134 ●158 ●192 http://www.pirobot.org/

updated 2016-10-24 09:02:59 -0500

ngrennan
1 ●1 ●1

I have a demo running on my robot that enables people to stand in front of the Kinect (which is the robot's head) and move their arms, then the robot moves its arms in a similar fashion. (Thanks to Taylor Veltrop!) My question is that as one user moves away and another user takes their place and assumes the Psi pose, is there any way to avoid the calibration phase? If it's necessary, then I guess I don't want to avoid it. But this earlier question suggests that it is not necessary. Since calibration some times takes a long time, it would be nice to skip it if possible.

Thanks!

patrick

http://www.pirobot.org

edit retag flag offensive close merge delete

add a comment

1 Answer

Sort by » oldest newest most voted

answered 2011-04-17 08:15:54 -0500

Thorsten
61 ●1 ●1 ●4

As i mentioned, all works fine with saving the calibration of the first user and asign it to Ebers user in szene. It might Be necessary to decide weather a Skeleton is a plausible user or not. I use the torso quality and some other measurements (bone lengths) to decide weather there is a real user in scene...

You can use the Save/Load calibration data from the OpenNi API... Unfortunately i found no way to save it, so the First user has to calibrate with the PSI Pose...