Henrik Andreasson and Todor Stoyanov
Real Time Registration of RGB-D Data using Local Visual Features and 3D-NDT Registration
Proc. Semantic Perception, Mapping and Exploration Workshop (SPME 2012) at the IEEE International Conference on Robotics and Automation (ICRA 2012)
Abstract: Recent increased popularity of RGB-D capable sensors in robotics has resulted in a surge of related RGB-D registration methods. This paper presents several RGB-D registration algorithms based on combinations between local visual feature and geometric registration. Fast and accurate transformation refinement is obtained by using a recently proposed geometric registration algorithm, based on the Three-Dimensional Normal Distributions Transform (3D-NDT). Results obtained on standard data sets have demonstrated mean translational errors on the order of 1 cm and rotational errors bellow 1 degree, at frame processing rates of about 15 Hz.
Download:
Paper: [PDF (1.5MB)].
Presentation: .
@INPROCEEDINGS{Andreasson_etal:SPME:2012,
  AUTHOR = {Andreasson, Henrik and Stoyanov, Todor},
  TITLE = {{Real Time Registration of RGB-D Data using Local Visual Features and 3D-NDT Registration}},
  BOOKTITLE = {Semantic Perception, Mapping and Exploration Workshop (SPME)},
  YEAR = {2012},
  MONTH = {May 14},
  ADRESS = {St. Paul, MI, USA},
  PAGES = {}
}