ABSTRACT
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.
- A. Elgammal, D. Harwood, and L. Davis, "Non-parametric model for background subtraction," in Proc. European Conf. on Computer Vision, Dublin, Ireland, volume II, 2000, pp. 751--767.]] Google ScholarDigital Library
- N. Friedman and S. Russell, "Image segmentation in video sequences," in Thirteenth Conf. on Uncertainty in Artificial Intelligence(UAI), 1997, pp. 175--181.]]Google Scholar
- A. Gelman, J. Carlin, H. Stern, and D. Rubin, Bayesian Data Analysis. Chapman and Hall, second edition, 2003.]]Google Scholar
- T. Horprasert, D. Harwood, and L. Davis, "A statistical approach for real-time robust background subtraction and shadow detection," in ICCV Frame-rate Workshop, 1999.]]Google Scholar
- S. Jabri, Z. Duric, H. Wechsler, and A. Rosenfeld, "Location of people in video images using adaptive fusion of color and edge information," in Proc. 15th Int'l Conf. on Pattern Recognition, Barcelona, Spain, volume 4, 2000, pp. 627--630.]] Google ScholarDigital Library
- K. Javed, O. Shafique and M. Shah, "A hierarchical approach to robust background subtraction using color and gradient information," in IEEE Workshop on Motion and Video Computing, 2002.]] Google ScholarDigital Library
- K.-P. Karman and A. von Brandt, "Moving object recognition using an adaptive background memory," in Capellini, editor, Time-varying Image Processing and Moving Object Recognition, volume II, (Amsterdam, The Netherlands), Elsevier, 1990, pp. 297--307.]]Google Scholar
- L. Li, W. Huang, I. Gu, and Q. Tian, "Foreground object detection from videos containing complex background," in ACM Multimedia, 2003.]] Google ScholarDigital Library
- A. Mittal and N. Paragios, "Motion-based background subtraction using adaptive kernel density estimation," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Washington, DC, volume II, 2004, pp. 302--309.]]Google Scholar
- C. Stauffer and E. Grimson, "Adaptive background mixture models for real-time tracking," in Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Fort Collins, CO, volume II, 1999, pp. 246--252.]]Google Scholar
- K. Toyama, J. Krumm, B. Brumitt, and B. Meyers, "Wall ower: Principles and practice of background maintenance," in Proc. 7th Intl. Conf. on Computer Vision, Kerkyra, Greece, 1999, pp. 255--261.]]Google Scholar
- C. Wren, A. Azarbayejani, T. Darell, and A. Pentland, "Pfinder: Real-time tracking of the human body," IEEE Trans. Pattern Anal. Machine Intell., vol. 19, pp. 780--785, 1997.]] Google ScholarDigital Library
Index Terms
- Bayesian background modeling for foreground detection
Recommendations
Nonparametric background generation
A novel background generation method based on nonparametric background model is presented for background subtraction. We introduce a new model, named as effect components description (ECD), to model the variation of the background, by which we can ...
A Hybrid Background Subtraction Method with Background and Foreground Candidates Detection
Background subtraction for motion detection is often used in video surveillance systems. However, difficulties in bootstrapping restrict its development. This article proposes a novel hybrid background subtraction technique to solve this problem. For ...
Effective S-? Background Estimation for Video Background Generation
APSCC '08: Proceedings of the 2008 IEEE Asia-Pacific Services Computing ConferenceMotion detection is a very important function in an intelligent video surveillance system. In order to detect the moving objects, it is necessary to generate the correct background image for each frame of the surveillance video. By subtracting the ...
Comments