The site is read-only. Please transition to use Robotics Stack Exchange
| ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange |
 | 1 | initial version |
That sounds like what I would expect based on this explanation in the viso2_ros wiki:
NOTE: The coordinate frame of the camera is expected to be the optical frame, which means x is pointing right, y downwards and z from the camera into the scene.
The wiki also explains:
To be able to calculate robot motion based on camera motion, the transformation from the camera frame to the robot frame has to be known.
So you need to change the frame which your camera is outputting images on to be something other than odom (like /camera_link), and then you need to define the /camera_link to /base_link transform.
ROS Answers is licensed under Creative Commons Attribution 3.0 Content on this site is licensed under a Creative Commons Attribution Share Alike 3.0 license.
