BACKGROUND SUBTRACTION USING BELIEF PROPAGATION

Hee-il Hahn

2011

Abstract

It is challenging to detect foreground objects when background includes an illumination variation, shadow or structural variation due to their motion. Basically pixel-based background models suffer from statistical randomness of each pixel. This paper proposes an algorithm that incorporates Markov random field(MRF) model into pixel-based background modelling to achieve more accurate foreground detection. Under the assumptions the distance between the pixel on the input image and the corresponding background model and the difference between the scene estimates of the spatio-temporally neighboring pixels are exponentially distributed, a recursive approach for estimating the MRF regularizing parameters is proposed. The proposed method alternates between estimating the parameters with the intermediate foreground detection results and detecting the foreground with the estimated parameters, after computing them with the detection results of the pixel-based background subtraction. Extensive experiment is conducted with several videos recorded both indoors and outdoors to compare the proposed method with the codebook-based algorithm.

References

  1. Stauffer, C., Grimson, W. E. L., 1999. Adaptive background mixture models for real-time tracking. IEEE International Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 246-252.
  2. Elgammal, A., Duraiswami, R., Harwood, D., Davis, L. S., 2002. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proc. IEEE, vol. 90, no. 7, pp. 1151- 1163.
  3. Kim, K., Chalidabhongse, T. H., Harwood, D., 2005. Real-time foreground-background segmentation using codebook model. Elsevier Real-Time Imaging, vol. 11, pp. 172-185.
  4. Migdal, J., Grimson, W. E., 2005. Background subtraction using Markov thresholds. Proceedings of the IEEE Workshop on Motion and Video Computing (WACV/MOTION'05).
  5. Wu, M., Peng, X., 2010. Spatio-temporal context for codebook-based dynamic background subtraction. International Journal of Electronics and Communications, pp. 739-747.
  6. Chen, Y., Chen, C., Huang, C., Hung, Y., 2007. Efficient hierarchical method for background subtraction. Pattern Recognition, pp. 2706-2715.
  7. Yedidia, J. S., Freeman W. T., Weiss, Y., 2002. Understanding belief propagation and its generalizetions. TR-2001-22.
  8. Zhang, L., Seitz, S. M., 2007. Estimating optimal parameters for MRF stereo from a single image pair. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no.2, pp. 331-342.
  9. McHugh, J. M., Konrad, J., Saligrama, V., Jodoin, P., 2009. Foreground-adaptive background subtraction. IEEE Signal Processing Letters, vol.16, issue 5, pp.390-393.
  10. Xu, X., Huang, T. S., 2008. A loopy belief propagation approach for robust background estimation. CVPR 2008, pp. 23-28.
Download


Paper Citation


in Harvard Style

Hahn H. (2011). BACKGROUND SUBTRACTION USING BELIEF PROPAGATION . In Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-8425-75-1, pages 281-286. DOI: 10.5220/0003444102810286


in Bibtex Style

@conference{icinco11,
author={Hee-il Hahn},
title={BACKGROUND SUBTRACTION USING BELIEF PROPAGATION},
booktitle={Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2011},
pages={281-286},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003444102810286},
isbn={978-989-8425-75-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 8th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - BACKGROUND SUBTRACTION USING BELIEF PROPAGATION
SN - 978-989-8425-75-1
AU - Hahn H.
PY - 2011
SP - 281
EP - 286
DO - 10.5220/0003444102810286