Segmentation by Combining Optical Flow with a Color Model

Adrian Ulges, Thomas Breuel

In: Proceedings of the International Conference on Pattern Recognition. International Conference on Pattern Recognition (ICPR) December 8-11 Tampa Florida United States IEEE Computer Society 12/2008.


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.


vidseg.pdf (pdf, 537 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence