| A.P. Mangan and R.T. Whitaker. Partitioning 3D Surface Meshes Using Watershed Segmentation. In IEEE TVCG,vol- ume 5 (4), pages 308--321, 1999. |
....of a mesh into more visually meaningful regions, or parts. Although an abundance of literature is available for range image segmentation [3] mesh segmentation has only recently become of interest. From the literature, we suggest two algorithms represent the state of the art: Mangan and Whitaker [7] and Wu and Levine [17] Other works include [16, 2, 12, 18, 9] Mangan and Whitaker coin the term, mesh segmentation, and propose a top down bobsledding implementation of watershed segmentation from image processing. With a different approach, Wu and Levine propose a novel algorithm based on the ....
....None of these assumptions are necessary for our algorithm. Also, we note a difference in computational complexity. Wu and Levine solve a set of linear equations with an iterative conjugate gradient method. With our curvature [15] we have a direct closed form technique. Mangan and Whitaker [7], on the other hand, propose a very robust segmentation strategy, but their method yields an ad hoc segmentation without support from a theory such as the minima rule. Building on these methods, we seek an algorithm that strictly adheres to the minima rule and yet leverages the robustness of a ....
[Article contains additional citation context not shown here]
A. P. Mangan and R. T. Whitaker. Partitioning 3D surface meshes using watershed segmentation. IEEE Transactions on Visualization and Computer Graphics, 5(4):308-- 321, Oct.--Dec. 1999.
....mean curvature for triangle meshes. As with the angle excess methods, Desbrun et al. use interior angles of triangles for their formulation. With a different approach, Gourley [17] presents a total pseudo curvature based on the dispersion of face normals around a vertex while Mangan and Whitaker [26] refine this measure as the norm of a covariance matrix for these face normals. This pseudo curvature is proportional to the magnitude of Gaussian curvature. A novel algorithm from Wu and Levine [49] is a physics based approach where they simulate the distribution of charge density across a mesh. ....
....sign information that our ad hoc umbrella method resolves. We further note that our classification scheme does not enforce crease continuity, i.e. topologically link crease vertices. If such topological connectivity is important, we suggest morphological operations [38] or watershed methods [26]. The final caveat relates to the neighborhood definition. The neighborhood algorithm is a fast marching method that begins at the vertex of interest v as the center and marches out to form the neighborhood M v . For curvature estimation as the algorithm marches outward, we check the ....
A. P. Mangan and R. T. Whitaker, Partitioning 3D surface meshes using watershed segmentation, IEEE Trans. Visual. Comput. Graphics 5, 1999, 308--321.
....diverse stopping criteria (see Section 3.4) Another difference is that we measure distortion in a different way that is better suited for triangular meshes, as in [13] There are also several methods which specifically address the problem of mesh partitioning or segmentation. Mangan and Whitaker [12] extend the watershed algorithm for image decomposition to handle polyhedral surfaces. Li et al. 10] use skeletonization and space sweeping to decompose a given mesh into topologically and geometrically homogeneous components. Since these segmentation methods are driven by other applications, ....
A. P. Mangan and R. T. Whitaker. Partitioning 3d surface meshes using watershed segmentation. IEEE Transactions on Visualization and Computer Graphics, 5(4):308--321, October - December 1999. ISSN 1077-2626.
....artifacts showing in a) are removed in b) by appropriate segmentation. If performed at run time (i.e. if used in systems such as [RP94, SLS 99] the segmentation of the triangulated depth mesh has to be done very quickly. Therefore, sophisticated range image segmentation methods such as [MW99] cannot be applied since most of these approaches as reported in [HJBJ 96] are far too slow for our purpose. In [MMB97] the notion of connectedness is defined to disambiguate the connected and disconnected mesh regions. Each triangle in the mesh is designated as either low connectedness or ....
A. Mangan and R.T. Whitaker. Partitioning 3d surface meshes using watershed segmentation. IEEE Transactions on Visualization and Computer Graphics, 5(4):308--321, 1999.
....some recent spectral graph theorybased algorithms [44, 36, 30] appeared to perform better than other techniques. They make decisions on where to partition the data using global information. We will extend the normalized cut framework in [44] to 3D range image segmentation in the next section. [31] proposes a technique for segmenting surface meshes by generalizing morphological watersheds. It is not directly relevant to the problem we are looking into because we consider segmentation as a very fundamental data processing stage which should happen at least in parallel to mesh reconstruction, ....
MANGAN, A.P., AND WHITAKER, R.T. Partitioning 3D Surface Meshes Using Watershed Segmentation. In IEEE Trans. on Visualization and Computer Graphics, 5(4), 1999, pp.308-321.
No context found.
A. P. Mangan, R. T. Whitaker, Partitioning 3D surface meshes using watershed segmentation, IEEE Transactions on Visualization and Computer Graphics 5 (4) (1999) 308--321.
No context found.
A.P. Mangan and R.T. Whitaker. Partitioning 3D Surface Meshes Using Watershed Segmentation. In IEEE TVCG,vol- ume 5 (4), pages 308--321, 1999.
No context found.
A. P. Mangan and R. T. Whitaker. Partitioning 3D surface meshes using watershed segmentation. IEEE Transactions on Visualization and Computer Graphics, 5(4):308--321, October 1999.
No context found.
Alan P. Mangan and Ross T. Whitaker. Partitioning 3D surface meshes using watershed segmentation. IEEE Transactions on Visualization and Computer Graphics, 5(4), 1999.
No context found.
A. P. Mangan, R. T. Whitaker, Partitioning 3d surface meshes using watershed segmentation, IEEE Transactions on Visualization and Computer Graphics 5 (4) (1999) 308--321.
No context found.
A. P. Mangan and R. T. Whitaker. Partitioning 3d surface meshes using watershed segmentation. IEEE Transactions on Visualization and Computer Graphics, 5(4), 1999.
No context found.
MANGAN, A.P., AND WHITAKER, R.T. Partitioning 3D Surface Meshes Using Watershed Segmentation. In IEEE Trans. on Visualization and Computer Graphics, 5(4), 1999, pp.308-321.
No context found.
A. P. Mangan and R. T. Whitaker. Partitioning 3d surface meshes using watershed segmentation. IEEE Transactions on Visualization and Computer Graphics, 5(4), 1999.
No context found.
A. P. Mangan and R. T. Whitaker. Partitioning 3D surface meshes using watershed segmentation. IEEE Transactions on Visualization and Computer Graphics, 5(4):308-- 321, Oct.--Dec. 1999.
No context found.
A.P. Mangan and R.T. Whitaker. Partitioning 3D surface meshes using watershed segmentation, IEEE Transactions on Visualization and Computer Graphics, Vol. 5 No. 4, 308-321, 1999.
No context found.
Mangan , A., Whitaker, R. Partitioning 3D Surface Meshes Using Watershed Segmentation. IEEE Visualization and Computer Graphics, vol 5, No 4, 308-21, 1999.
No context found.
A.P. Mangan and R.T. Whitaker. Partitioning 3D Surface Meshes Using Watershed Segmentation. In IEEE TVCG,vol- ume 5 (4), pages 308--321, 1999.
No context found.
Mangan A.P., Whitaker R.T. Partitioning 3D Surface Meshes Using Watershed Segmentation, IEEE Transactions on Visualization and Computer Graphics, Vol. 5 No. 4 (1999), 308-321.
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