Multi-region unstructured volume segmentation using tetrahedron filling
- Los Alamos National Laboratory
- MDI, INSTITUTES
- UC DAVIS
Segmentation is one of the most common operations in image processing, and while there are several solutions already present in the literature, they each have their own benefits and drawbacks that make them well-suited for some types of data and not for others. We focus on the problem of breaking an image into multiple regions in a single segmentation pass, while supporting both voxel and scattered point data. To solve this problem, we begin with a set of potential boundary points and use a Delaunay triangulation to complete the boundaries. We use heuristic- and interaction-driven Voronoi clustering to find reasonable groupings of tetrahedra. Apart from the computation of the Delaunay triangulation, our algorithm has linear time complexity with respect to the number of tetrahedra.
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC52-06NA25396
- OSTI ID:
- 993124
- Report Number(s):
- LA-UR-10-01594; LA-UR-10-1594; TRN: US201023%%243
- Resource Relation:
- Conference: 5th International Symp. 3D Data Processing, Visualization & Transmission ; May 17, 2010 ; Paris, France
- Country of Publication:
- United States
- Language:
- English
Similar Records
Region and edge-adaptive sampling and boundary completion for segmentation
Image segmentation by hierarchial agglomeration of polygons using ecological statistics