When matching regions from "similar" images, one typically has the problem of missing counterparts due to local or even global variations of segmentation fineness. Matching segmentation hierarchies, however, not only increases the chances of finding counterparts, but also allows us to exploit the manifold constraints coming from the topological relations between the regions in a hierarchy. In this paper we match hierarchies from panoramic images by constructing an association graph G/sub A/ whose vertices represent potential matches and whose edges indicate topological consistency. Specifically, a maximal [maximum] weight clique of GA corresponds to a topologically consistent mapping with maximal [maximum] total similarity. To find "heavy" cliques, we adapt a greedy pivoting-based heuristic to the weighted case. Experiments on pairs of panoramic images demonstrate the reliability of the results.
Hierarchical matching of panoramic images
01.01.2003
364617 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Hierarchical Matching of Panoramic Images
British Library Conference Proceedings | 2003
|Horizon matching for localizing unordered panoramic images
British Library Online Contents | 2010
|Hierarchical contour matching in medical images
British Library Online Contents | 1996
|Characterization of Errors in Compositing Panoramic Images
British Library Online Contents | 1999
|Constructing Virtual Cities by Using Panoramic Images
British Library Online Contents | 2004
|