Full Text:   <1742>

CLC number: TP391.41

On-line Access: 2009-10-21

Received: 2008-10-24

Revision Accepted: 2009-02-10

Crosschecked: 2009-08-14

Cited: 3

Clicked: 3291

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
1. Reference List
Open peer comments

Journal of Zhejiang University SCIENCE A 2009 Vol.10 No.12 P.1750~1758

http://doi.org/10.1631/jzus.A0820743


Bayesian moving object detection in dynamic scenes using an adaptive foreground model


Author(s):  Sheng-yang YU, Fang-lin WANG, Yun-feng XUE, Jie YANG

Affiliation(s):  Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200240, China

Corresponding email(s):   whizstorm@sjtu.edu.cn

Key Words:  Moving object detection, Foreground model, Kernel density estimation (KDE), MAP-MRF estimation


Sheng-yang YU, Fang-lin WANG, Yun-feng XUE, Jie YANG. Bayesian moving object detection in dynamic scenes using an adaptive foreground model[J]. Journal of Zhejiang University Science A, 2009, 10(12): 1750~1758.

@article{title="Bayesian moving object detection in dynamic scenes using an adaptive foreground model",
author="Sheng-yang YU, Fang-lin WANG, Yun-feng XUE, Jie YANG",
journal="Journal of Zhejiang University Science A",
volume="10",
number="12",
pages="1750~1758",
year="2009",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.A0820743"
}

%0 Journal Article
%T Bayesian moving object detection in dynamic scenes using an adaptive foreground model
%A Sheng-yang YU
%A Fang-lin WANG
%A Yun-feng XUE
%A Jie YANG
%J Journal of Zhejiang University SCIENCE A
%V 10
%N 12
%P 1750~1758
%@ 1673-565X
%D 2009
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.A0820743

TY - JOUR
T1 - Bayesian moving object detection in dynamic scenes using an adaptive foreground model
A1 - Sheng-yang YU
A1 - Fang-lin WANG
A1 - Yun-feng XUE
A1 - Jie YANG
J0 - Journal of Zhejiang University Science A
VL - 10
IS - 12
SP - 1750
EP - 1758
%@ 1673-565X
Y1 - 2009
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.A0820743


Abstract: 
Accurate detection of moving objects is an important step in stable tracking or recognition. By using a nonparametric density estimation method over a joint domain-range representation of image pixels, the correlation between neighboring pixels can be used to achieve high levels of detection accuracy in the presence of dynamic background. However, color similarity between foreground and background will cause many foreground pixels to be misclassified. In this paper, an adaptive foreground model is exploited to detect moving objects in dynamic scenes. The foreground model provides an effective description of foreground by adaptively combining the temporal persistence and spatial coherence of moving objects. Building on the advantages of MAP-MRF (the maximum a posteriori in the Markov random field) decision framework, the proposed method performs well in addressing the challenging problem of missed detection caused by similarity in color between foreground and background pixels. Experimental results on real dynamic scenes show that the proposed method is robust and efficient.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1] Deng, Y., Kenney, C., Moore, M.S., Manjunath, B.S., 1999. Peer Group Filtering and Perceptual Color Image Quantization. Proc. IEEE Int. Symp. on Circuits and Systems, 4:21-24.

[2] Elgammal, A., Harwood, D., Davis, L., 2002. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proc. IEEE, 90(7):1151-1163.

[3] Greig, D., Porteous, B., Seheult, A., 1989. Extract maximum a posteriori estimation for binary images. J. Royal Stat. Soc. Ser. B, 51(2):271-279.

[4] Kolmogorov, V., Zabih, R., 2004. What energy functions can be minimized via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell., 26(2):147-159.

[5] Lu, L., Hager, G.D., 2007. A Nonparametric Treatment for Location/Segmentation Based Visual Tracking. IEEE Conf. on Computer Vision and Pattern Recognition, p.1-8.

[6] Mahamud, S., 2006. Comparing Belief Propagation and Graph Cuts for Novelty Detection. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, p.1154-1159.

[7] Parzen, E., 1962. On estimation of a probability density and mode. Ann. Math. Statist., 33(3):1065-1076.

[8] Sheikh, Y., Shah, M., 2005. Bayesian modeling of dynamic scenes for object detection. IEEE Trans. Pattern Anal. Mach. Intell., 27(11):1778-1792.

[9] Stauffer, C., Grimson, W., 2000. Learning patterns of activity using real-time tracking. IEEE Trans. Pattern Anal. Mach. Intell., 22(8):747-757.

[10] Sun, J., Zhang, W., Tang, X., Shum, H.Y., 2006. Background cut. LNCS, 3952:628-641.

[11] Wand, M., Jones, M., 1995. Kernel Smoothing. In: Cox, D.R., Hinkley, D.V., Reid, N., et al. (Eds.), Monographs on Statistics and Applied Probability. Chapman and Hall, New York.

[12] Wang, Y., Tan, T., 2002. Adaptive Foreground and Shadow Detection in Image Sequences. Proc. Int. Conf. on Pattern Recognition, p.983-986.

[13] Wren, C., Azarbayejani, A., Darrel, T., Pentland, A.P., 1997. Pfinder: real time tracking of the human body. IEEE Trans. Pattern Anal. Mach. Intell., 19(7):780-785.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE