Image Projection onto Flat LiDAR Point Cloud Surfaces to Create Dense and Smooth 3D Color Maps

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 30
  • Download : 0
This paper proposes an area-wise method to build aesthetically pleasing RGB-D data by projecting camera images onto LiDAR point clouds corrected by Graph SLAM. In particular, the focus is on projecting images to corresponding flat surfaces, extracted as plane equations by RANSAC. The newly created data boasts a camera-like view even in 3D due to its dense, yet smooth flat point clouds. However, since this method is only limited to planar surfaces, other 3D data points that could not be separated as planes had to suffer poor quality due to sparse and rough LiDAR point clouds.
Publisher
Korea Robot Society
Issue Date
2020-06-22
Language
English
Citation

Int'l Conf. on Ubiquitous Robots (UR) 2020

URI
http://hdl.handle.net/10203/275083
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0