Abstract | ||
---|---|---|
f' scanner raw.dataS ' 5 The objective of our research reported here is to show the various processing steps on all levels of a computer vision system required to interpret and describe road maps. First, the foundation for the recognition process is laid by comput- ing two sets of distance skeletons. They are termed endo- and exo-skeleton and are symmetrical with respect to the boundary between foreground and background of a binary raster image. The skeletons are derived from a novel im- plementation of Blum's concept of the MAT in the semi- continuum which preserves important features such as Eu- clidean metric and correct topology. To eliminate noise and quantization effects a new regularization method has been devised based on which the MAT is pruned to its stable inner branches. After the removal of artefacts and further simpli- firation of the skeleton the recognition of meaningful com- plex structures is accomplished in several steps with the aid of a growing amount of domain-specific knowledge. Scene knowledge helps to verify (local) hypotheses in a larger con- text and to arrive at a consistent interpretation throughout thr scenr. The selection of the object-oriented programming paradigm proved to be very effective. |
Year | Venue | Keywords |
---|---|---|
1990 | MVA | object oriented programming,computer vision,knowledge base |
Field | DocType | Citations |
Computer vision,Raster graphics,Pattern recognition,Programming paradigm,Computer science,Euclidean distance,Regularization (mathematics),Scanner,Artificial intelligence,Quantization (signal processing),Binary number | Conference | 3 |
PageRank | References | Authors |
0.59 | 2 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Markus Ilg | 1 | 10 | 3.68 |
robert l ogniewicz | 2 | 18 | 5.17 |