Authors:
Ales Jelinek
and
Adam Ligocki
Affiliation:
Central European Institute of Technology, Purkynova 123, Brno and Czech Republic
Keyword(s):
Line, Plane, Registration, Least Squares, Optimization, Rigid Transformation, Data Fitting.
Related
Ontology
Subjects/Areas/Topics:
Informatics in Control, Automation and Robotics
;
Optimization Problems in Signal Processing
;
Robotics and Automation
;
Sensors Fusion
;
Signal Processing, Sensors, Systems Modeling and Control
;
Vision, Recognition and Reconstruction
Abstract:
This paper deals with the Line-Plane registration problem. First we introduce the matter of geometrical object fitting and show the specificity of the Line-Plane combination. Then the method is derived to fulfil all usual demands we put on a registration algorithm. Our algorithm works on any number of corresponding Line-Plane pairs higher than three, providing more accurate results and better convergence, as this number gets higher. Although the computation is non-linear by its nature, benefits of the least squares optimization were preserved. The algorithm is divided into a linear part dependant on the amount of input data and a non-linear part, which is not, keeping efficiency in case of large data sets. All important features were experimentally tested and proved to work.