Convergent iterative closest-point algorithm to accomodate anisotropic and inhomogenous localization error

• Verfasst von: Maier-Hein, Lena [VerfasserIn]
• Verfasst von: Franz, Alfred Michael [VerfasserIn]
• Verfasst von: Schmidt, Mirko [VerfasserIn]
• Verfasst von: Meinzer, Hans-Peter [VerfasserIn]
• Titel: Convergent iterative closest-point algorithm to accomodate anisotropic and inhomogenous localization error
• Verf.angabe: L. Maier-Hein, A. M. Franz, T. R. dos Santos, M. Schmidt, M. Fangerau, H. Meinzer, and J. M. Fitzpatrick
• Jahr: 2012
• Umfang: 13 S.
• Fussnoten: Date of publication: 20 December 2011 ; Gesehen am 11.10.2018
• Titel Quelle: Enthalten in: Institute of Electrical and Electronics EngineersIEEE transactions on pattern analysis and machine intelligence
• Ort Quelle: New York, NY : IEEE, 1979
• Jahr Quelle: 2012
• Band/Heft Quelle: 34(2012), 8, Seite 1520-1532
• ISSN Quelle: 1939-3539
• DOI: doi:10.1109/TPAMI.2011.248
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: 3D models
• Sach-SW: Algorithm design and analysis
• Sach-SW: Algorithms
• Sach-SW: Animals
• Sach-SW: anisotropic localization error
• Sach-SW: anisotropic weighting.
• Sach-SW: Anisotropy
• Sach-SW: Cameras
• Sach-SW: computational geometry
• Sach-SW: convergence of numerical methods
• Sach-SW: convergent iterative closest-point algorithm
• Sach-SW: covariance matrices
• Sach-SW: Covariance matrix
• Sach-SW: data alignment
• Sach-SW: Diagnostic Imaging
• Sach-SW: geometric alignment
• Sach-SW: Head
• Sach-SW: Humans
• Sach-SW: ICP
• Sach-SW: ICP algorithm
• Sach-SW: Image Processing, Computer-Assisted
• Sach-SW: image registration
• Sach-SW: inhomogenous localization error
• Sach-SW: isotropic Gaussian noise
• Sach-SW: Iterative closest point algorithm
• Sach-SW: iterative methods
• Sach-SW: Measurement
• Sach-SW: medical image processing
• Sach-SW: medical imaging data
• Sach-SW: mesh extraction
• Sach-SW: mesh generation
• Sach-SW: Noise
• Sach-SW: partial overlapping surfaces
• Sach-SW: partial surface registration
• Sach-SW: point correspondences
• Sach-SW: point-based registration
• Sach-SW: point-based surface registration
• Sach-SW: Principal Component Analysis
• Sach-SW: Rabbits
• Sach-SW: Registration
• Sach-SW: solid modelling
• Sach-SW: surface algorithms
• Sach-SW: surface meshes
• Sach-SW: Three dimensional displays
• K10plus-PPN: 1581767331

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 this paper, we show that this assumption may lead to errors and generalize the ICP such that it can account for anisotropic and inhomogenous localization errors. We 1) provide a formal description of the algorithm, 2) extend it to registration of partially overlapping surfaces, 3) prove its convergence, 4) derive the required covariance matrices for a set of selected applications, and 5) present means for optimizing the runtime. An evaluation on publicly available surface meshes as well as on a set of meshes extracted from medical imaging data shows a dramatic increase in accuracy compared to the original ICP, especially in the case of partial surface registration. As point-based surface registration is a central component in various applications, the potential impact of the proposed method is high.