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. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ICPR.2008.4761579 | 19TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1-6 |
Keywords | Field | DocType |
optical flow,pixel,image segmentation,motion compensation,probability,graph cut,histograms,gaussian noise,color model,error rate,computer vision | Computer vision,Scale-space segmentation,Pattern recognition,Computer science,Motion compensation,Image segmentation,Parametric statistics,Artificial intelligence,Color model,Optical flow,Gaussian noise,Mixture model | Conference |
ISSN | Citations | PageRank |
1051-4651 | 1 | 0.37 |
References | Authors | |
11 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Adrian Ulges | 1 | 328 | 26.61 |
Thomas M. Breuel | 2 | 2362 | 219.10 |