DMCA
Wide-baseline multiple-view correspondences (2003)
Cached
Download Links
- [www.vision.ee.ethz.ch]
- [groups.inf.ed.ac.uk]
- DBLP
Other Repositories/Bibliography
| Venue: | In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition |
| Citations: | 50 - 6 self |
BibTeX
@INPROCEEDINGS{Ferrari03wide-baselinemultiple-view,
author = {Vittorio Ferrari and Tinne Tuytelaars and Luc Van Gool},
title = {Wide-baseline multiple-view correspondences},
booktitle = {In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
year = {2003}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We present a novel approach for establishing multiple-view feature correspondences along an unordered set of images taken from substantially different viewpoints. While recently several wide-baseline stereo (WBS) algorithms have appeared, the N-view case is largely unexplored. In this paper, an established WBS algorithm is used to extract and match features in pairs of views. The pairwise matches are first integrated into disjoint feature tracks, each representing a single physical surface patch in several views. By exploiting the interplay between the tracks, they are extended over more views, while unrelated image features are removed. Similarity and spatial relationships between the features are simultaneously used. The output consists of many reliable and accurate feature tracks, strongly connecting the input views. Applications include 3D reconstruction and object recognition. The proposed approach is not restricted to the particular choice of features and matching criteria. It can extend any method that provides feature correspondences between pairs of images. 1.
Keyphrases
wide-baseline multiple-view correspondence object recognition particular choice several wide-baseline stereo accurate feature track unordered set n-view case single physical surface patch spatial relationship unrelated image feature novel approach feature correspondence pairwise match wb algorithm different viewpoint several view input view multiple-view feature correspondence disjoint feature track
