Separating background and foregroundin video based on a nonparametric Bayesian model


Journal Article

Separating background and foreground in video is a fundamental problem in computer vision. We present a Bayesian hierarchical model to address this challenge, and apply it to video with dynamic scenes. The model uses a nonparametric prior, a beta-bernoulli process, for both the background and foreground representation. Additionally, the model uses neighborhood information of each pixel to encourage group clustering of the foreground. A collapsed Gibbs sampler is used for efficient posterior inference. Experimental results show competitive performance of the proposed model. © 2011 IEEE.

Full Text

Duke Authors

Cited Authors

  • Ding, X; Carin, L

Published Date

  • September 5, 2011

Published In

  • Ieee Workshop on Statistical Signal Processing Proceedings

Start / End Page

  • 321 - 324

Digital Object Identifier (DOI)

  • 10.1109/SSP.2011.5967692

Citation Source

  • Scopus