A coarse-to-fine algorithm for 3D registration based on wavelet decomposition

Authors:
C. Torre-Ferrero;S. Robla;E. G. Sarabia;J. R. Llata
Affiliations:
Electronics Technology, Systems and Automation Engineering Department, University of Cantabria, Santander, Spain;Electronics Technology, Systems and Automation Engineering Department, University of Cantabria, Santander, Spain;Electronics Technology, Systems and Automation Engineering Department, University of Cantabria, Santander, Spain;Electronics Technology, Systems and Automation Engineering Department, University of Cantabria, Santander, Spain
Venue:
ICS'08 Proceedings of the 12th WSEAS international conference on Systems
Year:
2008

Citing 8
Cited 0

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Method for Registration of 3-D Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
Object modelling by registration of multiple range images

Image and Vision Computing - Special issue: range image understanding
Surface registration by matching oriented points

NRC '97 Proceedings of the International Conference on Recent Advances in 3-D Digital Imaging and Modeling
Free-Form Surface Registration Using Surface Signatures

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Harmonic shape images: a three-dimensional free-form surface representation and its applications in surface matching

Harmonic shape images: a three-dimensional free-form surface representation and its applications in surface matching
The correspondence framework for 3D surface matching algorithms

Computer Vision and Image Understanding
3D registration by using an alternative 3D shape representation

ISCGAV'07 Proceedings of the 7th WSEAS International Conference on Signal Processing, Computational Geometry & Artificial Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a coarse-to-fine algorithm for 3D registration that uses an alternative 3D Shape Representation: CIRCON (Cylindrical Image of Radial CONtours). Two point clouds can be aligned using their corresponding circon images for searching for correspondences. In order to accelerate this search, a coarse-to-fine approach based on wavelet image decomposition will be applied to the circon images. This permits to reduce, for each resolution level, the amount of indexes to be evaluated. The information obtained by the surface matching process is then used for calculating a coarse transformation (translation and rotation) between both surfaces; in such a way that two point clouds whose relative pose is unknown can be aligned.