H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. In CVPR 91, Maui, Hawai, June 1991.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....noisy volumetric images to segment anatomical shapes [16] 17] These models were used in a variety of volumetric images [18] Later, H. Delingette proposed to use deformable discrete meshes, called Simplex Meshes, quite efficient to interactively segment anatomical structures in volumetric images [19] [20] An important property of simplex meshes stems from the fact that each node has exactly 3 neighbors, therefore allowing a simple approximation of the mean curvature. This property allowed H. Delingette to propose dedicated schemes to preserve the regularity of the deformable surfaces during ....

H. Delingette, M. Hebert, and K. Ikeuchi, "Shape representation and image segmentation using deformable surfaces," Image and Vision Computing, vol. 10, no. 3, pp. 132--144, Apr. 1992.

....open problem [11, 36, 58] For 3D object models, most shape analysis work has focused on registration, recognition, and pairwise matching of surface meshes. For instance, representations for registering and matching 3D surfaces include Extended Gaussian Images [38] Spherical Attribute Images [27, 28], and Harmonic Shape Images [99] Unfortunately, these previous methods usually assume that a topologically valid surface mesh is available for every object. Volumetric dissimilarity measures based on wavelets [34] or Earth Mover s Distance [73] rely upon a priori registration of objects ....

.... axes [10] and skeletons [19, 37, 83] require a consistent model of the object s boundary and interior, which is difficult to reconstruct for highly degenerate computer graphics models [11, 36, 58] Other shape representations, such as Extended Gaussian Images [38] Spherical Attribute Images [27, 28], moments [68, 86] and wavelets [34] require a priori registration into a canonical coordinate system, which is difficult to achieve robustly. Finally, statistical shape descriptors, such as feature vectors [29] and shape distributions [62] are usually not discriminating enough to distinguish ....

H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. Image and vision computing, 10(3):132--144, April 1992.

....Among these existing shape representations, our work is most related to the shape descriptors that map the 3D shape of an object to a spherical domain. Some examples include Extended Gaussian Images [36] Orientation Histograms [10] Spherical Extent Functions [37] and Spherical Attribute Images [38, 39]. However, these prior approaches map local surface features (surface orientation, curvature, etc. to points on a sphere, and thus they are sensitive to noise in 3D surface data. In contrast, our reflective symmetry descriptor maps global features (integrals over the entire surface) to each ....

Delingette, H., Hebert, M., Ikeuchi, K.: Shape representation and image segmentation using deformable surfaces. Image and Vision Computing 10 (1992) 132--144

....of a set of planar facets where, it should be mentioned, the facet edges are straight lines. With this kind of technique, sometimes referred to as polyhedral or tessellated modeling, a solid is decomposed in a set of cells, and each cell can keep its particular geometric and topological structures [4]. In these cases, several kinds of features can be stored in the tessellated model [5] The model developed in our study is based on this method: tessellated representation. In practice, the problem of modeling involves several tasks which could be independent: acquiring object data, registering ....

H.Delingete, M.Hebert, K. Ikeuchi. Shape Representation and Image Segmentation Using Deformable Surfaces, image And Vision Computing, 10(3) Abril 1992

....yangchen iris.usc.edu between the model structures and the object surface elements. Previous researchers have studied such mappings in a variety ways using different representation schemes and model fitting methods. Examples of these approaches are the dynamic system using energy minimization of [Delingette et al. 91] and the dynamic mesh of [Terzopoulos Vasilescu 91] and [Vasilescu Terzopoulos 92] One of the drawbacks of these approaches is that it is yet not known how to formulate the system in such a way that it is guaranteed to converge to the desired result, or in other words, they must rely on an ....

....91] introduced a shape reconstruction algorithm using a dynamic mesh that can dynamically adjust its parameters to adapt to the input data. They also extended this approach by introducing an attraction force from 3 D inputs for shape description [Vasilescu Terzopoulos 92] Delingette et al. Delingette et al. 91] proposed a deformable model with internal smoothness energy and external forces from both the input data and features. There are other deformable model approaches that differ in representation schemes of the model and in the approaches to solving the system (see [Cohen Cohen 93] and [McInerney ....

H. Delingette, M. Hebert, K. Ikeuchi, "Shape Representation and Image Segmentation Using Deformable Surfaces," Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), pp.467-472, Maui, HI, June 1991.

....was introduced fairly recently by Terzopoulos et al. 15] They proposed a dynamic deformable cylinder model constructed from generalized splines and developed force field techniques to fit the model to image data. The dynamic model fitting approach is being pursued by several researchers [7, 10, 3, 4, 16, 6, 17], as it is in this paper. This paper presents a physics based approach to the reconstruction of object shape and nonrigid motion tracking using a 3D deformable balloon model. The model is dynamic, and its deformation is governed by the laws of nonrigid motion. The formulation of the motion ....

H. Delingette, M. Hebert, and K. Ikeuchi. Shape Representation and Image Segmentation Using Deformable Surfaces. In Proc. IEEE Conf. Comp. Vis. Pat. Rec., pages 467--472, June 1991.

....was introduced fairly recently by Terzopoulos et al. 13] They proposed a dynamic deformable cylinder model constructed from generalized splines and developed force field techniques to fit the model to image data. The dynamic model fitting approach is being pursued by several researchers [6, 9, 2, 3, 14, 5, 15], as it is in this paper. This paper presents a physics based approach to surface reconstruction using an elastically deformable sheet model. The model is based on physically motivated multi dimensional generalizations of classical 1 Fellow, Canadian Institute for Advanced Research splines. ....

H. Delingette, M. Hebert, and K. Ikeuchi. Shape Representation and Image SegmentationUsing Deformable Surfaces. In Proc. IEEE Conf. Comp. Vis. Pat. Rec., pages 467--472, June 1991.

....functions [60] arch height functions [40] and size functions [55, 56] have no analogs for 3D models. Shape matching has also been well studied for 3D objects. For instance, representations for registering and matching 3D surfaces include Extended Gaussian Images [32] Spherical Attribute Images [20, 21], Harmonic Shape Images [61] and Spin Images [36] Unfortunately, these previous methods usually assume that a topologically valid surface mesh or an explicit volume is available for every object. In addition, volumetric dissimilarity measures based on wavelets [28] or Earth Mover s Distance [48] ....

H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. Image and vision computing, 10(3):132--144, April 1992.

....functions [59] arch height functions [40] and size functions [55] have no analogs for 3D models. Shape matching has also been well studied for 3D objects. For instance, representations for registering and matching 3D surfaces include Extended Gaussian Images [31] Spherical Attribute Images [20, 21], Harmonic Shape Images [60] and Spin Images [35] Unfortunately, these previous methods usually assume that a topologically valid surface mesh or an explicit volume is available for every object. In addition, volumetric dissimilarity measures based wavelets [27] or Earth Mover s Distance [48] ....

H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. Image and vision computing, 10(3):132--144, April 1992.

....scenarios where this technique is not effective. Three dimensional deformable surfaces or balloons , on the other hand, are potentially faster, make more effective use of the 3D data, and, in many situations, require less user input and guidance. Several variants have been developed [12] [13], 14] 15] 16] 17] In this paper, we present a natural extension of our ACID framework that is suitable for deformable surfaces. In particular, we develop topology adaptive deformable surfaces, dubbed T surfaces [18] for use on volume images. After a brief review of the planar, T snakes ....

H. Delingette, M. Hebert, and K. Ikeuchi, "Shape representation and image segmentation using deformable surfaces," Image and Vision Computing, vol. 10, no. 3, pp. 132--144, April 1992.

....and for tracking moving objects in computer vision. Following the advent of the dynamic shape modeling paradigm, there was a flurry of research activity in the area, with numerous application specific modifications to the modeling primitives, and external forces derived from data constraints [9, 25, 26, 27, 28, 6, 7]. However, the aforementioned schemes for shape modeling have two serious limitations the dependence of the final surface shape on the initial guess made to start the numerical reconstruction procedure, and a strong assumption on the object s topology. The first of these deficiencies stems from ....

H. Delingette, M. Hebert, and K. Ikeuchi, "Shape representation and image segmentation using deformable models," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 467--472, Maui Hawaii, June 1991.

....and for tracking moving objects in computer vision. Following the advent of the dynamic shape modeling paradigm, there was a flurry of research activity in the area, with numerous application specific modifications to the modeling primitives, and external forces derived from data constraints [10, 30, 31, 32, 7]. However, the aforementioned schemes for shape modeling have two serious limitations the dependence of the final surface shape on the initial guess made to start the numerical reconstruction procedure, and an assumption that the object is of a known topology. The first of these deficiencies ....

H. Delingette, M. Hebert, and K. Ikeuchi, "Shape representation and image segmentation using deformable models," in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 467--472, Maui Hawaii, June 1991.

....approach, the data points are located directly by the curve through the minimization of the potential (see Section 2.1) Moreover, all the points of the curve are influenced by the attraction forces from the image. Mixed version. Recently a combination of the previous approaches was proposed in [16]. Two potentials are defined. A data energy term is used to represent an attraction of the surface to the closest data point, which yields a force that is linear when close to the data and decreases to zero when far from the point. The data energy is the same as our potential using the Chamfer ....

H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. In Proc. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Maui, Hawai, June 1991.

....constraints that must be enforced when the mesh is built. Consu ucting meshes that fit input data and that satisfy some constraints is possible based on the optimization techniques originally introduced in [26] and [16] We use an extension of the deformable surfaces algorithms introduced in [8] to compute the meshes. As in the EGI algorithms, each node of the mesh is mapped onto a regular mesh on the unit sphere, and a quantity that reflects the local surface curvature at the node is stored at the corresponding node on the sphere. Instead of using a discrete approximation of the ....

....parallel to the normal vector of the plane formed by its three neighbors and passing by the center of the neighbors. These two conditions ensure that the mesh is a good approximation of the surface while guaranteeing that it is an intrinsic representation. The formalism of deformable surfaces [8] is applied to deform the mesh until it satisfies these criteria. Specifically, each node is subject to two types of forces. The first type of forces brings a node closer to the input sur face, while the second type forces the node to satisfy the normal constraint. Let F o be the force of the ....

[Article contains additional citation context not shown here]

Delingette, H., Hebert, M. and Ikeuchi, K., "Shape Representation and Image Segmentation Using Deformable Surfaces", Image and Vision Computing, Vol. 10, No. 3, p. 132April 1992

No context found.

H. Delingette, M. Hebert and K. Ikeuchi, Shape representation and image segmentation using deformable RFIA'98 IIl 30 Clermont-Ferrand Janvier 1998.

....the shape of an object, existing representations of 3D free form objects may be regarded as either global or local. Examples of global representations are algebraic polynomials[49] 80] spherical representations such as EGI (extended Gaussian Image) 40] SAI (Spherical Attribute Image) 34] 36] 19][20] and COSMOS (Curvedness Orientation Shape Map On Sphere) 25] triangles and crease angle histograms[9] and HOT (High Order Tangent) curves[47] Although global representations can describe the overall shape of an object, they have difficulties in representing objects of arbitrary topology or ....

H. Dellingette, M. Hebert and K. Ikeuchi, Shape representation and image segmentation using deformable surfaces, Image and Vision Computing, Vol.10, No.3, pp. 132-144, 1992.

....model a dynamic behavior resulting in a more intuitive interaction. First introduced by Terzopoulos, Kass and Witkin[10] 20] to extract contour or axialsymmetric surfaces from video images, elastically deformable models have been extensively used both in computer vision and computer graphics[4][6]. The equations of motion are derived by minimizing quadratic elastic energies such as the bivariate generalized spline functionals[18] through some variational principals. Solutions are computed over time by using finite differences with explicit [6] or semi implicit[4] schemes, or ....

....in computer vision and computer graphics[4] 6] The equations of motion are derived by minimizing quadratic elastic energies such as the bivariate generalized spline functionals[18] through some variational principals. Solutions are computed over time by using finite differences with explicit [6] or semi implicit[4] schemes, or finite element analysis[2] External constraints have been designed to fit range data[6] 20] to enhance the user interface or to simulate physical phenomena such as object contact, viscoelasticity or animated characters. Though appealing for their clay like ....

[Article contains additional citation context not shown here]

H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. In IEEE Computer Vision and Pattern Recognition (CVPR91), pages 467--472, June 1991.

....proposed by Terzopoulos et al. and have attracted significant interest for their intuitive and clay like be 0 This work was supported in part by a grant from Digital Equipement Corporation havior. Several researchers have applied the dynamic model tting scheme to range data or medical images[2][4][8] 7] Elastic models successfully address the problem of shape control. However, few researchers have proposed general adaptive reconstruction techniques for solving both geometric and topological aspects. 8] 9] 6] This paper presents a shape reconstruction algorithm that ooeers both geometric ....

H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. In IEEE Computer Vision and Pattern Recognition (CVPR91), pages 467472, June 1991.

No context found.

H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. In CVPR 91, Maui, Hawai, June 1991.

No context found.

H. Delingette, M. Hebert, and K. Ikeuchi, "Shape Representation and Image Segmentation Using Deformable Surfaces," Image and Vision Computing, vol. 10, no. 3, pp. 132-144, 1992.

No context found.

H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. Image and Vision Computing, 10:132--144, 1992.

No context found.

Delingette, H., Hebert, M., Ikeuchi, K.: Shape representation and image segmentation using deformable surfaces. Image and Vision Computing 10 (1992) 132--144

No context found.

H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. In Proc. Comp. Vision Pattern Recog., pages 467--472, June 1991.

No context found.

H. Delingette, M. Hebert, and K. Ikeuchi. Shape representation and image segmentation using deformable surfaces. In Proc. 1991.

No context found.

H. Delingette, M. Hebert, K. Ikeuchi, "Shape Representation and Image Segmentation Using Deformable Surfaces", in Computer Vision and Pattern Recognition, 1991, pp467-472.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC