The robustness of shape recovery based on deformable models depends in general, on the relative difference of position and topology of the initial model with respect to the data: a close initialization with correct topology guarantees a proper recovery of the object. Furthermore, the closeness of the initial model greatly influences the time of computation needed for the recovery. In this paper, we propose a method for initializing deformable models from range data or volumetric images. The proposed method solves two distinct problems. First, we use the topological segmentation of volumetric images in order to recover the approximate topology of the object. Second, we use an efficient mesh sampling algorithm to control the number of vertices of the initial model. The method takes into account missing data and outliers.
Initialization of deformable models from 3D data
01.01.1998
764771 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Initialization of Deformable Models from 3D Data
British Library Conference Proceedings | 1998
|Velcro Surfaces: Fast Initialization of Deformable Models
British Library Online Contents | 1997
|Efficient Deformable Template Detection and Localization without User Initialization
British Library Online Contents | 2000
|Constrained Recovery of Deformable Models from Range Data
British Library Conference Proceedings | 1994
|Europäisches Patentamt | 2021
|