Segmentation by Combining Optical Flow with a Color Model

Adrian Ulges, Thomas Breuel
Proceedings of the International Conference on Pattern Recognition, Tampa, Florida, USA, IEEE Computer Society, 12/2008

Abstract:

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.

Files:

  vidseg.pdf

BibTex:

@inproceedings{ ULGE2008,
	Title = {Segmentation by Combining Optical Flow with a Color Model},
	Author = {Adrian Ulges and Thomas Breuel},
	BookTitle = {Proceedings of the International Conference on Pattern Recognition},
	Month = {12},
	Year = {2008},
	Publisher = {IEEE Computer Society}
}

     
Last modified:: 30.08.2016