Abstract In this paper we introduce a principled approach to modeling the image brightness constraint for optical flow algorithms. Using a simple noise model, we derive a probabilistic representation for optical flow. This representation subsumes existing approaches to flow modeling, provides insights into the behaviour and limitations of existing methods and leads to modified algorithms that outperform other approaches that use the brightness constraint. Based on this representation we develop algorithms for flow estimation using different smoothness assumptions, namely constant and affine flow. Experiments on standard data sets demonstrate the superiority of our approach.
Revisiting the Brightness Constraint: Probabilistic Formulation and Algorithms
Computer Vision – ECCV 2006 ; 4 ; 177-188
Lecture Notes in Computer Science ; 3953 , 4
2006-01-01
12 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Revisiting the Brightness Constraint: Probabilistic Formulation and Algorithms
British Library Conference Proceedings | 2006
|Motion Estimation Relaxing the Constancy Brightness Constraint
British Library Conference Proceedings | 1994
|A probabilistic trajectory constraint modeler
IEEE | 2016
|Rank Constraints for Homographies over Two Views: Revisiting the Rank Four Constraint
British Library Online Contents | 2009
|Constraint handling in multiobjective genetic algorithms
AIAA | 2000
|