Abstract | ||
---|---|---|
We describe our intermediate level representation and processing of partial 3D wire frame data, obtained from edge-based stereo depth reconstruction systems. We use a double representation schema, based both on CAD winged-edge-like data-structures and on frames. We also use a goal-oriented grouping mechanism combining a data-drive bottom-up indexing, mainly in the form of a potential connect graph, and a knowledge-driven top-down grouping, whose methods are distributed along the structural hierarchy of the knowledge-base. The best candidate instances of higher-level geometrical structures are sought using these grouping mechanisms. They are then matched against their template-class and, when possible, completed using WFRL [Burbello 1991], a knowledge-based system capable of verifying and imposing constraints on incomplete wire frame structures. |
Year | DOI | Venue |
---|---|---|
1991 | 10.1007/3-540-54712-6_243 | AI*IA |
Keywords | Field | DocType |
stereo vision data,high-level data structures,top down,knowledge based system,connected graph,knowledge base,stereo vision,bottom up,indexation,data structure,goal orientation | CAD,Stereo cameras,Computer vision,Data structure,Pattern recognition,Stereopsis,Computer science,Search engine indexing,Artificial intelligence,Hierarchy,Schema (psychology),Computer stereo vision | Conference |
ISBN | Citations | PageRank |
3-540-54712-6 | 0 | 0.34 |
References | Authors | |
3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fidenzio Burbello | 1 | 0 | 0.34 |
Stephen Pollard | 2 | 192 | 121.36 |
John Porrill | 3 | 352 | 85.11 |
John E. W. Mayhew | 4 | 233 | 322.10 |