ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | Q&A
Ask Your Question

Opencv solvepnp() and ROS tf

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

davinci gravatar image

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

tfoote gravatar image

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

1 Answer

Sort by ยป oldest newest most voted

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

tfoote gravatar image

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 more

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account.

Add Answer

Question Tools

1 follower


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

Seen: 1,027 times

Last updated: Jan 22 '14