Motion Detail Preserving Optical Flow Estimation
Top Cited Papers
- 13 December 2011
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 34 (9), 1744-1757
- https://doi.org/10.1109/tpami.2011.236
Abstract
A common problem of optical flow estimation in the multiscale variational framework is that fine motion structures cannot always be correctly estimated, especially for regions with significant and abrupt displacement variation. A novel extended coarse-to-fine (EC2F) refinement framework is introduced in this paper to address this issue, which reduces the reliance of flow estimates on their initial values propagated from the coarse level and enables recovering many motion details in each scale. The contribution of this paper also includes adaptation of the objective function to handle outliers and development of a new optimization procedure. The effectiveness of our algorithm is demonstrated by Middlebury optical flow benchmarkmarking and by experiments on challenging examples that involve large-displacement motion.Keywords
This publication has 30 references indexed in Scilit:
- Secrets of optical flow estimation and their principlesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Motion estimation with non-local total variation regularizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human MotionInternational Journal of Computer Vision, 2009
- Anisotropic Huber-L1 Optical FlowPublished by British Machine Vision Association and Society for Pattern Recognition ,2009
- A New Alternating Minimization Algorithm for Total Variation Image ReconstructionSIAM Journal on Imaging Sciences, 2008
- Fixed-Point Continuation for $\ell_1$-Minimization: Methodology and ConvergenceSIAM Journal on Optimization, 2008
- Lucas/Kanade Meets Horn/Schunck: Combining Local and Global Optic Flow MethodsInternational Journal of Computer Vision, 2005
- Towards ultimate motion estimation: combining highest accuracy with real-time performancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Computing optical flow with physical models of brightness variationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- DETERMINING OPTICAL-FLOWArtificial Intelligence, 1980