Elastic Registration of 3D Objects
نویسنده
چکیده
Description: In this project, a non-trivial extension of the nonlinear framework for aligning planar shapes (Recovering Diffeomorfic Shape Deformations without Correspondences [8]) is developed for 3D elastic 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 volumes.
منابع مشابه
On Analyzing Symmetry of Objects using Elastic Deformations
We introduce a framework for analyzing symmetry of 2D and 3D objects using elastic deformations of their boundaries. The basic idea is to define spaces of elastic shapes and to compute shortest (geodesic) paths between the objects and their reflections using a Riemannian structure. Elastic matching, based on optimal (nonlinear) re-parameterizations of curves, provides a better registration of p...
متن کاملLog-unbiased elastic image registration with spatial constraint for 3D CT lung images
Registering diagnostic lung CT and whole body CT images is a difficult task due to their acquisition under different breathing stages. We have implemented a novel framework for 3D CT lung image registration which combines elastic registration with log-unbiased deformations and a spatially variable constraint to reduce image folding and retain the rigidity of the bones. A comparison of the propo...
متن کاملLarge Deformation Inverse Consistent Elastic Image Registration
This paper presents a new image registration algorithm that accommodates locally large nonlinear deformations. The algorithm concurrently estimates the forward and reverse transformations between a pair of images while minimizing the inverse consistency error between the transformations. It assumes that the two images to be registered contain topologically similar objects and were collected usi...
متن کاملIncorporation of Landmark Error Ellipsoids for Image Registration Basedon
We present an approach for elastic registration of 3D tomographic images which is based on a set of corresponding anatomical point landmarks and takes into account anisotropic landmark localization errors in form of 3D error ellipsoids. The 3D error ellipsoids are directly estimated from the image data. The performance of our approach is demonstrated for 2D and 3D MR images of the human brain.
متن کامل3D Modelling of Under Ground Burried Objects Based on Ground Penetration Radar
There is a growing demand for mapping and 3D modelling of buried objects such as pipelines, agricultural hetitage, landmines and other buried objects. Usually, large scale and high resolution maps from these objects are needed. Manually map generation and modeling of these objects are cost and time consuming and is dependent on lots of resources. Therefore, automating the subsurface mapping and...
متن کامل