Sciweavers

ICASSP
2007
IEEE

Multiple View Region Matching as a Lagrangian Optimization Problem

14 years 6 months ago
Multiple View Region Matching as a Lagrangian Optimization Problem
A method to establish correspondences between regions belonging to independent segmentations of multiple views of a scene is presented. The trade-off between color similarity and projective similarity of the matching regions is formulated in terms of a constrained optimization, analogous to a Rate-Distortion budget-constrained allocation problem, and solved using Lagrangian optimization techniques.
Felipe Calderero, Ferran Marqués, Antonio O
Added 02 Jun 2010
Updated 02 Jun 2010
Type Conference
Year 2007
Where ICASSP
Authors Felipe Calderero, Ferran Marqués, Antonio Ortega
Comments (0)