Abstract Establishing correspondence between features of a set of images has been a long-standing issue amongst the computer vision community. We propose a method that solves the multi-frame correspondence problem by imposing a rank constraint on the observed scene, i.e. rigidity is assumed. Since our algorithm is based solely on a geometrical (global) criterion, it does not suffer from issues usually associated to local methods, such as the aperture problem. We model feature matching by introducing the assignment tensor, which allows simultaneous feature alignment for all images, thus providing a coherent solution to the calibrated multi-frame correspondence problem in a single step of linear complexity. Also, an iterative method is presented that is able to cope with the non-calibrated case. Moreover, our method is able to seamlessly reject a large number of outliers in every image, thus also handling occlusion in an integrated manner.
Optimal Multi-frame Correspondence with Assignment Tensors
Computer Vision – ECCV 2006 ; 8 ; 490-501
Lecture Notes in Computer Science ; 3953 , 8
2006-01-01
12 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Optimal Multi-frame Correspondence with Assignment Tensors
British Library Conference Proceedings | 2006
|Optimal-flow minimum-cost correspondence assignment in particle flow tracking
British Library Online Contents | 2011
|Multi-Frame Correspondence Estimation Using Subspace Constraints
British Library Online Contents | 2002
|Identifying truck correspondence in multi-frame imagery
Elsevier | 2003
|British Library Online Contents | 2012
|