A unifying framework for non-linear registration of 3D objects

Zsolt Sánta, Z. Kato

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

An extension of our earlier work is proposed to find a non-linear aligning transformation between a pair of deformable 3D objects. The basic idea is to set up a system of nonlinear equations whose solution directly provides the parameters of the aligning transformation. Each equation is generated by integrating a nonlinear function over the object's domains. Thus the number of equations is determined by the number of adopted nonlinear functions yielding a flexible mechanism to generate sufficiently many equations. While classical approaches would establish correspondences between the shapes, our method works without landmarks. Experiments with 3D polynomial and thin plate spline deformations confirm the performance of the framework.

Original languageEnglish
Title of host publication3rd IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2012 - Proceedings
Pages547-552
Number of pages6
DOIs
Publication statusPublished - 2012
Event3rd IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2012 - Kosice, Slovakia
Duration: Dec 2 2012Dec 5 2012

Other

Other3rd IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2012
CountrySlovakia
CityKosice
Period12/2/1212/5/12

Fingerprint

Nonlinear equations
Splines
Polynomials
experiment
performance
Experiments

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing
  • Communication

Cite this

Sánta, Z., & Kato, Z. (2012). A unifying framework for non-linear registration of 3D objects. In 3rd IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2012 - Proceedings (pp. 547-552). [6422041] https://doi.org/10.1109/CogInfoCom.2012.6422041

A unifying framework for non-linear registration of 3D objects. / Sánta, Zsolt; Kato, Z.

3rd IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2012 - Proceedings. 2012. p. 547-552 6422041.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sánta, Z & Kato, Z 2012, A unifying framework for non-linear registration of 3D objects. in 3rd IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2012 - Proceedings., 6422041, pp. 547-552, 3rd IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2012, Kosice, Slovakia, 12/2/12. https://doi.org/10.1109/CogInfoCom.2012.6422041
Sánta Z, Kato Z. A unifying framework for non-linear registration of 3D objects. In 3rd IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2012 - Proceedings. 2012. p. 547-552. 6422041 https://doi.org/10.1109/CogInfoCom.2012.6422041
Sánta, Zsolt ; Kato, Z. / A unifying framework for non-linear registration of 3D objects. 3rd IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2012 - Proceedings. 2012. pp. 547-552
@inproceedings{aea6744387524c77ad262612cca23d5b,
title = "A unifying framework for non-linear registration of 3D objects",
abstract = "An extension of our earlier work is proposed to find a non-linear aligning transformation between a pair of deformable 3D objects. The basic idea is to set up a system of nonlinear equations whose solution directly provides the parameters of the aligning transformation. Each equation is generated by integrating a nonlinear function over the object's domains. Thus the number of equations is determined by the number of adopted nonlinear functions yielding a flexible mechanism to generate sufficiently many equations. While classical approaches would establish correspondences between the shapes, our method works without landmarks. Experiments with 3D polynomial and thin plate spline deformations confirm the performance of the framework.",
author = "Zsolt S{\'a}nta and Z. Kato",
year = "2012",
doi = "10.1109/CogInfoCom.2012.6422041",
language = "English",
isbn = "9781467351874",
pages = "547--552",
booktitle = "3rd IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2012 - Proceedings",

}

TY - GEN

T1 - A unifying framework for non-linear registration of 3D objects

AU - Sánta, Zsolt

AU - Kato, Z.

PY - 2012

Y1 - 2012

N2 - An extension of our earlier work is proposed to find a non-linear aligning transformation between a pair of deformable 3D objects. The basic idea is to set up a system of nonlinear equations whose solution directly provides the parameters of the aligning transformation. Each equation is generated by integrating a nonlinear function over the object's domains. Thus the number of equations is determined by the number of adopted nonlinear functions yielding a flexible mechanism to generate sufficiently many equations. While classical approaches would establish correspondences between the shapes, our method works without landmarks. Experiments with 3D polynomial and thin plate spline deformations confirm the performance of the framework.

AB - An extension of our earlier work is proposed to find a non-linear aligning transformation between a pair of deformable 3D objects. The basic idea is to set up a system of nonlinear equations whose solution directly provides the parameters of the aligning transformation. Each equation is generated by integrating a nonlinear function over the object's domains. Thus the number of equations is determined by the number of adopted nonlinear functions yielding a flexible mechanism to generate sufficiently many equations. While classical approaches would establish correspondences between the shapes, our method works without landmarks. Experiments with 3D polynomial and thin plate spline deformations confirm the performance of the framework.

UR - http://www.scopus.com/inward/record.url?scp=84874425740&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874425740&partnerID=8YFLogxK

U2 - 10.1109/CogInfoCom.2012.6422041

DO - 10.1109/CogInfoCom.2012.6422041

M3 - Conference contribution

SN - 9781467351874

SP - 547

EP - 552

BT - 3rd IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2012 - Proceedings

ER -