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.

Opencv solvepnp() and ROS tf

asked 2014-01-21 01:12:08 -0500

davinci

2563 ●35 ●45 ●60

updated 2014-01-27 11:54:49 -0500

tfoote

58457 ●128 ●550 ●526 http://www.ros.org/

I am using solvepnp() to get the pose of a checkerboard. But with a static marker and a moving camera the rotations and translations are not correct. solvepnp() gives a rotation in Rodriguez angles and a translation. Through a rotation matrix I convert this to quaternions. And broadcast this to tf as the transformation camera to marker. But is this the correct way?

edit retag flag offensive close merge delete

add a comment

1 Answer

Sort by » oldest newest most voted

answered 2014-01-22 07:37:17 -0500

tfoote

58457 ●128 ●550 ●526 http://www.ros.org/

Nominally your approach sounds correct. You want to find the pose of the checkerboard int the frame of the camera and then publish a transform from the camera to the checkerboard.

edit flag offensive delete link

add a comment

Question Tools

1 follower

Stats

Asked: 2014-01-21 01:12:08 -0500

Seen: 1,099 times

Last updated: Jan 22 '14

Opencv solvepnp() and ROS tf edit

1 Answer

Question Tools

Stats

Related questions

Opencv solvepnp() and ROS tf