2012
DOI: 10.1109/tpami.2011.248
|View full text |Cite
|
Sign up to set email alerts
|

Convergent Iterative Closest-Point Algorithm to Accomodate Anisotropic and Inhomogenous Localization Error

Abstract: Since its introduction in the early 1990s, the Iterative Closest Point (ICP) algorithm has become one of the most well-known methods for geometric alignment of 3D models. Given two roughly aligned shapes represented by two point sets, the algorithm iteratively establishes point correspondences given the current alignment of the data and computes a rigid transformation accordingly. From a statistical point of view, however, it implicitly assumes that the points are observed with isotropic Gaussian noise. In thi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
90
0

Year Published

2013
2013
2022
2022

Publication Types

Select...
7
3

Relationship

1
9

Authors

Journals

citations
Cited by 120 publications
(90 citation statements)
references
References 35 publications
0
90
0
Order By: Relevance
“…Further offline experiments were made with a generalization of the ICP, accounting for anisotropic uncertainties-the so-called anisotropic ICP [30] (A-ICP)-and its respective trimmed version [22]. The A-ICP is intended for surfaces affected by intense noise and copes with different resolutions.…”
Section: Discussionmentioning
confidence: 99%
“…Further offline experiments were made with a generalization of the ICP, accounting for anisotropic uncertainties-the so-called anisotropic ICP [30] (A-ICP)-and its respective trimmed version [22]. The A-ICP is intended for surfaces affected by intense noise and copes with different resolutions.…”
Section: Discussionmentioning
confidence: 99%
“…For this purpose, the nearest neighbor function based on the Euclidean distance was applied to establish correspondences between a reconstructed surface and the reference surface. We have also considered accounting for anisotropic reconstruction errors by using a weighted distance, as proposed in [46], [47], but this would have implied estimating a covariance matrix of localization error for each reconstructed point and thus led to a much higher complexity.…”
Section: ) Validation Criterion Comparison Function and Quality Indexmentioning
confidence: 99%
“…Again, it is interesting to see the link between multimodal image fusion-the application this method was intended for in Levin et al [29]-and image-guided therapy, where ICP is still a mainstay when it comes to merging physical coordinate systems such as a stereotactic fixation device or a LINAC to the coordinate system of a volume image [32][33][34][35][36][37][38][39][40][41][42][43]. In the latter case, surface points can either be manually digitized by using a 3D input device [40] or by optical or other non-invasive technologies such as A-mode US [34,35,37,41,42].…”
Section: Surface-and Gradient Based Methodsmentioning
confidence: 99%