Title :
Geometric optimization
Author :
Hinker, Paul ; Hansen, Charles
Author_Institution :
Los Alamos Nat. Lab., NM, USA
Abstract :
An algorithm is presented which describes an application independent method for reducing the number of polygonal primitives required to faithfully represent an object. Reducing polygon count without a corresponding reduction in object detail is important for: achieving interactive frame rates in scientific visualization, reducing mass storage requirements, and facilitating the transmission of large, multi-timestep geometric data sets. This paper shows how coplanar and nearly coplanar polygons can be merged into larger complex polygons and re-triangulated into fewer simple polygons than originally required. The notable contributions of this paper are: (1) a method for quickly grouping polygons into nearly coplanar sets, (2) a fast approach for merging coplanar polygon sets and, (3) a simple, robust triangulation method for polygons created by 1 and 2. The central idea of the algorithm is the notion of treating polygonal data as a collection of segments and removing redundant segments to quickly form polygon hulls which represent the merged coplanar sets
Keywords :
computational geometry; data visualisation; image representation; object recognition; optimisation; algorithm; application independent method; complex polygons; geometric optimisation; interactive frame rates; large multi-time step geometric data sets; mass storage requirements; merged coplanar sets; nearly coplanar polygons; object representation; polygon count; polygon hulls; polygonal primitives; redundant segments; scientific visualization; segments; triangulation method; Computer graphics; Geometry; Hydrodynamics; Laboratories; Magnetic resonance imaging; Medical simulation; Merging; Optimization methods; Robustness; Solid modeling;
Conference_Titel :
Visualization, 1993. Visualization '93, Proceedings., IEEE Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
0-8186-3940-7
DOI :
10.1109/VISUAL.1993.398868