Hierarchical matching of panoramic images

Abstract

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.