Title :
Characterization of three-dimensional data with multidimensional deformable models based on B-splines in the fourier domain
Author :
Berenguer-Vidal, R. ; Verdú-Monedero, R. ; Morales-Sánchez, J. ; Larrey-Ruiz, J. ; Bastida-Jumilla, M.C.
Author_Institution :
Dipt. Tecnol. de la Informacion y las Comun., Univ. Politec. Cartagena, Cartagena, Spain
Abstract :
This paper presents the formulation and implementation of multidimensional deformable models in the frequency domain. The models are defined by finite element discretization, using B-splines as shape function. The frequency-based formulation allows us to obtain an efficient iterative system in matrix form, suitable for models of any dimension. The aim of this approach is the use of these models for fast segmentation and motion tracking of three-dimensional objects with non rigid motion or deformation from three-dimensional datasets. To show the results of the process, a two dimensional model is applied for the characterization of topographic data.
Keywords :
Fourier analysis; frequency-domain analysis; image motion analysis; image segmentation; iterative methods; matrix algebra; object tracking; splines (mathematics); B-splines; Fourier domain; fast image segmentation; frequency domain; iterative system; multidimensional deformable models; shape function; three-dimensional data characterization; three-dimensional datasets; three-dimensional object motion tracking; topographic data characterization; Active contours; Computational modeling; Data models; Deformable models; Mathematical model; Shape; Spline; B-spline; frequency domain; motion tracking; multidimensional deformable model; three-dimensional segmentation;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on
Conference_Location :
Prague
Print_ISBN :
978-1-4577-0538-0
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2011.5946502