Analysis of the Weighting 3D Coordinates Based on Theoretical Random Errors for RGB-D Data Registration
Main Article Content
Abstract
In this paper a weighting scheme based on theoretical random errors of 3D coordinates for RGB-D data registration
is introduced. Basically, three main points involved in the method are here discussed: the pairwise registration; the
weighting of 3D coordinates; and a global adjustment. The registration of point clouds pairs is done in two steps. In the fi rst step, the transformation parameters are obtained by a set of points, detected by the SIFT algorithm employed
in the 3D rigid body model, beside the Least Squares Method. The second step consists in refi ne the transformation
parameters obtained in the previous step using the ICP algorithm based on point-to-point approach. The inclusion of
weight values is made based on the disparity propagation covariance equations. The global consistency analysis is used
to refi ne the set of translation parameters simultaneously. Experiments in scenes with mean distance from the sensor/
target of 4 meters were conducted to evaluate the eff ectiveness of the proposed method and the results indicate the
potential of the method to the average value of the discrepancies below 4 centimeters.
Downloads
Metrics
Article Details
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
Authors who publish in this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors can enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) before and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (see "The Effect of Open Access").
