Consistent segmentation for optical flow estimation
Authors:
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (15505499) , 1308-1315
Abstract
In this paper, we propose a method for jointly computing optical flow and segmenting video while accounting for mixed pixels (matting). Our method is based on statistical modeling of an image pair using constraints on appearance and motion. Segments are viewed as overlapping regions with fractional (alpha) contributions. Bidirectional motion is estimated based on spatial coherence and similarity of segment colors. Our model is extended to video by chaining the pairwise models to produce a joint probability distribution to be maximized. To make the problem more tractable, we factorize the posterior distribution and iteratively minimize its parts. We demonstrate our method on frame interpolationKeywords
This publication has 19 references indexed in Scilit:
- Object based segmentation of video using color, motion and spatial information2005
- High-quality video view interpolation using a layered representation2004
- Video tooningACM Transactions on Graphics, 2004
- Smoothness in layers: Motion segmentation using nonparametric mixture estimation2002
- A global matching framework for stereo computation2002
- Factor graphs and the sum-product algorithmIEEE Transactions on Information Theory, 2001
- Region-based video coder using edge flow segmentation and hierarchical affine region matching1998
- A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants1998
- Spline-Based Image RegistrationInternational Journal of Computer Vision, 1997
- Representing moving images with layersIEEE Transactions on Image Processing, 1994