TR2005-033
A Bayesian Approach to Background Modeling
-
- "A Bayesian Approach to Background Modeling", IEEE Workshop on Machine Vision for Intelligent Vehicles (MVIV), June 2005, vol. 3, pp. 58.BibTeX TR2005-033 PDF
- @inproceedings{Tuzel2005jun,
- author = {Tuzel, O. and Porikli, F. and Meer, P.},
- title = {A Bayesian Approach to Background Modeling},
- booktitle = {IEEE Workshop on Machine Vision for Intelligent Vehicles (MVIV)},
- year = 2005,
- volume = 3,
- pages = 58,
- month = jun,
- issn = {1063-6919},
- url = {https://www.merl.com/publications/TR2005-033}
- }
,
- "A Bayesian Approach to Background Modeling", IEEE Workshop on Machine Vision for Intelligent Vehicles (MVIV), June 2005, vol. 3, pp. 58.
-
Research Areas:
Abstract:
Learning background statistics is an essential task for several visual surveillance applications such as incident detection and traffic management. In this paper, we propose a new method for modeling background statistics of dynamic scene. Each pixel is represented with layers of Gaussian distributions. Using recursive Bayesian learning, we estimate the probability distribution of mean and covariance of each Gaussian. The proposed algorithm preserves the multimodality of the background and estimates the number of necessary layers for representing each pixel. We compare our results with the Gaussian mixture background model. Experiments conducted on synthetic and video data demonstrate the superior performance of the proposed approach.
Related News & Events
-
NEWS MVIV 2005: publication by Oncel Tuzel and others Date: June 20, 2005
Where: IEEE Workshop on Machine Vision for Intelligent Vehicles (MVIV)
Research Area: Machine LearningBrief- The paper "A Bayesian Approach to Background Modeling" by Tuzel, O., Porikli, F. and Meer, P. was presented at the IEEE Workshop on Machine Vision for Intelligent Vehicles (MVIV).