The objective of this work is to enlarge the class of camera motions for which epipolar geometry and image correspondences can be computed automatically. This facilitates matching between quite disparate views-wide baseline stereo. Two extensions are made to the current small baseline algorithms: first, and most importantly, a viewpoint invariant measure is developed for assessing the affinity of corner neighbourhoods over image pairs; second, algorithms are given for generating putative corner matches between image pairs using local homographies. Two novel infrastructure developments are also described: the automatic generation of local homographies, and the combination of possibly conflicting sets of matches prior to RANSAC estimation. The wide baseline matching algorithm is demonstrated on a number of image pairs with varying relative motion, and for different scene types. All processing is automatic.
Wide baseline stereo matching
01.01.1998
1057739 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
British Library Conference Proceedings | 1998
|Wide-baseline stereo matching with line segments
IEEE | 2005
|Viewpoint Invariant Texture Matching and Wide Baseline Stereo
British Library Conference Proceedings | 2001
|Correspondence expansion for wide baseline stereo
IEEE | 2005
|