Segmentation by combining parametric optical flow with a color model

We present a simple but efficient model for object segmentation in video scenes that integrates motion and color information in a joint probabilistic framework. Optical flow is modeled using parametric motion with Gaussian noise. The color distribution of foreground and background is described by hi...

Full description

Saved in:
Bibliographic Details
Published in2008 19th International Conference on Pattern Recognition pp. 1 - 4
Main Authors Ulges, A., Breuel, T.M.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2008
Subjects
Colored noise
Computer vision
Image motion analysis
Image segmentation
Layout
Motion estimation
Motion segmentation
Nonlinear optics
Robustness
Sprites (computer)
Online AccessGet full text

Cover

More Information
Summary:We present a simple but efficient model for object segmentation in video scenes that integrates motion and color information in a joint probabilistic framework. Optical flow is modeled using parametric motion with Gaussian noise. The color distribution of foreground and background is described by histograms or Gaussian mixture models. Optimization is carried out using an efficient graph cut algorithm. In quantitative experiments on a variety of video data, we demonstrate that the proposed approach leads to significant reductions in error rates compared to a state-of-the-art motion-only segmentation.
ISBN:9781424421749
1424421748
ISSN:1051-4651
2831-7475
DOI:10.1109/ICPR.2008.4761579