Closed miguelriemoliveira closed 4 years ago
Yes, thanks. I will have that into account:
Being to close from the sensors so that the charuco is detected from the camera
I agree with all of the above.
My suggestion is to consider trying to do something like this (not sure if you should, but at least consider)
https://github.com/code-iai/iai_kinect2/tree/master/kinect2_calibration
where the pattern is held by a fixed mechanism. It can be a tripod or a chair (provided the segmentation works fine)
Hi @miguelriemoliveira and @eupedrosa
I recorded four rosbags today. Here they are: https://drive.google.com/file/d/1Dw241gu8epQz9HEXsD6ALUT3X3YtlNwT/view?usp=sharing.
Hi @aaguiar96 ,
Apart from the suckers (ventosas) and eventually the part about also saving the undistorted image I see no more possible improvements. We've come a long way from the first bag file. Should we close?
Yes @miguelriemoliveira.
Hi @aaguiar96 ,
This issue is just to collect the ideas of what we can do better in the next bag file.
longer time (4 or 5 mins)
record also joint_states (input for the robot_state_publisher to publish tfs). Do you have some in the system?
patten on landscape orientation
fix the vlp16_frame / velodyne link
X. ... more stuff ?? Please add)