3D registration of object on flat surface, how to best constrain ICP?
This post has NOT been accepted by the mailing list yet.
I have a number of point clouds of an object placed on a flat surface
and I am trying to find a good PCL pipeline to create a 3D mesh of the
I am getting depth images from 4 Realsense SR300 cameras located roughly
90 degrees apart around the vertical axis, and I still do not understand
how to best input this information into the ICP algorithm, somehow I
would like to detect the common planar component on all images and
constrain the ICP algorithm to do translations along this plane and
rotations around its normal.
After ICP I would remove the planar component to obtain the single
object point cloud, is this a good approach? I am new to PCL, any help