Local Layering for Joint Motion Estimation and Occlusion Detection
Authors:
- Deqing SunDSDeqing Sun
- Ce LiuCLCe Liu
- Hanspeter PfisterHPHanspeter Pfister
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1098-1105
Abstract
Most motion estimation algorithms (optical flow, layered models) cannot handle large amount of occlusion in textureless regions, as motion is often initialized with no occlusion assumption despite that occlusion may be included in the final objective. To handle such situations, we propose a local layering model where motion and occlusion relationships are inferred jointly. In particular, the uncertainties of occlusion relationships are retained so that motion is inferred by considering all the possibilities of local occlusion relationships. In addition, the local layering model handles articulated objects with self-occlusion. We demonstrate that the local layering model can handle motion and occlusion well for both challenging synthetic and real sequences.Keywords
This publication has 25 references indexed in Scilit:
- A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind ThemInternational Journal of Computer Vision, 2013
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012
- Learning to find occlusion regions2011
- Local layering2009
- Occlusion Boundaries from Motion: Low-Level Detection and Mid-Level ReasoningInternational Journal of Computer Vision, 2009
- FusionFlow: Discrete-continuous optimization for optical flow estimation2008
- On the Spatial Statistics of Optical FlowInternational Journal of Computer Vision, 2007
- Mixture models for optical flow computation2002
- Factor graphs and the sum-product algorithmIEEE Transactions on Information Theory, 2001
- Determining optical flowArtificial Intelligence, 1981