Structure- and motion-adaptive regularization for high accuracy optic flow
- 1 September 2009
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1663-1668
- https://doi.org/10.1109/iccv.2009.5459375
Abstract
The accurate estimation of motion in image sequences is of central importance to numerous computer vision applications. Most competitive algorithms compute flow fields by minimizing an energy made of a data and a regularity term. To date, the best performing methods rely on rather simple purely geometric regularizes favoring smooth motion. In this paper, we revisit regularization and show that appropriate adaptive regularization substantially improves the accuracy of estimated motion fields. In particular, we systematically evaluate regularizes which adoptively favor rigid body motion (if supported by the image data) and motion field discontinuities that coincide with discontinuities of the image structure. The proposed algorithm relies on sequential convex optimization, is real-time capable and outperforms all previously published algorithms by more than one average rank on the Middlebury optic flow benchmark.Keywords
This publication has 14 references indexed in Scilit:
- Duality TV-L1 flow with fundamental matrix priorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- A Variational Model for the Joint Recovery of the Fundamental Matrix and the Optical FlowLecture Notes in Computer Science, 2008
- A Database and Evaluation Methodology for Optical FlowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Highly Accurate Optic Flow Computation with Theoretically Justified WarpingInternational Journal of Computer Vision, 2006
- An Algorithm for Total Variation Minimization and ApplicationsJournal of Mathematical Imaging and Vision, 2004
- A framework for the robust estimation of optical flowPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Segmentation of visual motion by minimizing convex non-quadratic functionalsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A Theoretical Framework for Convex Regularizers in PDE-Based Computation of Image MotionInternational Journal of Computer Vision, 2001
- The fundamental matrix: Theory, algorithms, and stability analysisInternational Journal of Computer Vision, 1996
- An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image SequencesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1986