Skip to content

Latest commit

 

History

History
45 lines (31 loc) · 2.66 KB

File metadata and controls

45 lines (31 loc) · 2.66 KB

PointCloudRegistration-py

Testing 4 level point cloud registration

  1. filtering (remove noise)
  2. down sampling (reduce point)
  3. global registration (rough registration)
  4. local refinement (elaborate registration)

main dependencies

  • tkinter (user interface)
  • panda3d (scene graph)
  • open3d (point cloud)

Usage

Screenshot

View

mesh point cloud down sampled point cloud

In this screenshot, processing means down sampling and filtering. We just do 5 mm scale down sampling at now.

initial global registration result local registration result

We support point cloud registration by right buttons.
global point cloud registration -> using feature point ransac (open3d global registration)
local point cloud registration -> open3d g-icp

And we support changing to custom source or target by menu (just only obj file...)

TODO

다양한 PointCloud Registration Option을 넣을 수 있는 User Interface 추가