Cosmo L, Albarelli A, Bergamasco F, Torsello A, Rodola E, Cremers D (2016)
Publication Type: Conference contribution
Publication year: 2016
Publisher: Institute of Electrical and Electronics Engineers Inc.
Book Volume: 0
Pages Range: 3715-3720
Conference Proceedings Title: Proceedings - International Conference on Pattern Recognition
Event location: Cancun, MEX
ISBN: 9781509048472
DOI: 10.1109/ICPR.2016.7900212
Feature matching is a key step in most Computer Vision tasks involving several views of the same subject. In fact, it plays a crucial role for a successful reconstruction of 3D information of the corresponding material points. Typical approaches to construct stable feature tracks throughout a sequence of images operate via a two-step process: First, feature matches are extracted among all pairs of points of view; these matches are then given in input to a regularizer that provides a final, globally consistent solution. In this paper, we formulate this matching problem as a simultaneous optimization over the entire image collection, without requiring previously computed pairwise matches to be given as input. As our formulation operates directly in the space of feature across multiple images, the final matches are consistent by construction. Our matching problem has a natural interpretation as a non-cooperative game, which allows us to leverage tools and results from Game Theory. We performed a specially crafted set of experiments demonstrating that our approach compares favorably with the state of the art, while retaining a high computational efficiency.
APA:
Cosmo, L., Albarelli, A., Bergamasco, F., Torsello, A., Rodola, E., & Cremers, D. (2016). A game-theoretical approach for joint matching of multiple feature throughout unordered images. In Proceedings - International Conference on Pattern Recognition (pp. 3715-3720). Cancun, MEX: Institute of Electrical and Electronics Engineers Inc..
MLA:
Cosmo, Luca, et al. "A game-theoretical approach for joint matching of multiple feature throughout unordered images." Proceedings of the 23rd International Conference on Pattern Recognition, ICPR 2016, Cancun, MEX Institute of Electrical and Electronics Engineers Inc., 2016. 3715-3720.
BibTeX: Download