TR2005-101
| Bayesian Background Modeling for Foreground Detection | |||
| Citation: | Porikli, F.; Tuzel, O., "Bayesian Background Modeling for Foreground Detection", ACM International Workshop on Video Surveillance and Sensor Networks (VSSN), ISBN: 1-59593-242-9, pp. 55-28, November 2005 (ACM Press) | ||
| Date: | April 2006 | ||
| MERL Contact: | Fatih Porikli | ||
We propose a Bayesian learning method to capture the background statistics of a dynamic scene. We model each pixel as a set of layered normal distributions that compete with each other. Using a recursive Bayesian learning mechanism, we estimate not only the mean and variance but also the probability distribution of the mean and covariance of each model. This learning algorithm preserves the multimodality of the background process and is capable of estimating the number of required layers to represent each pixel. | |||
| |||
