Block-Wise Background Subtraction Based on Gaussian Mixture Models

Abstract:

The background subtraction of an image enables us to distinguish a moving object in a video sequence and enter higher levels of video processing. Background processing is an essential strategy for many video processing applications and its most primary method (utilized to determine the difference of sequential frames) is very rapid and easy, but not appropriate for complicated scenes. In this article we introduce a method to remove the false distinction of the foreground. In our proposed method the updating of which is automatic, a mixture of Gaussians have been used. In addition this method depends on the passage of time. The previously introduced methods are often based on processing on the pixel and ignore the neighbor pixels in order to improve the background. Our method does not make do with one pixel but rather benefits from a block of pixels in order to include all the pixels included in the block. Experimental findings indicate considerable developments in the proposed method which can quickly and without morphological filtering model the background using image supervising cameras placed in both inside and outside locations and lighting changes, repetitive motion from clutter and scene changes. Subsequently the moving object in the scene can appear for real-time tracking and recognition applications.

• Periodical: Applied Mechanics and Materials (Volumes 490-491)
• Pages: 1221-1227
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.490-491.1221
• Online since: January 2014
• Authors: Mehran Yazdi, Mohammad A. Bagherzadeh, Mehdi Jokar, Mohammad A. Abasi
• Keywords: Background Modeling, Background Subtraction, Gaussian Mixture Models, Motion Detection, Object Tracking, Video Surveillance

References

[1] L. Li, W. Huang, I.Y.H. Gu, Q. Tian, Statistical modeling of complex background for foreground object detection, IEEE Trans. Image Process. 13 (11) (2004) 1459-1472.

DOI: 10.1109/tip.2004.836169

[2] A. Elgammal, D. Harwood, L.S. Davis, Non-parametric model for background subtraction, in: Proceedings of European Conference on Computer Vision, 2000, pp.751-767.

DOI: 10.1007/3-540-45053-x_48

[3] T. Horprasert, D. Harwood, L.S. Davis, A statistical approach for real-time robust background subtraction and shadow detection, in: Proceedings of IEEE ICCV Frame-Rate Workshop, 1999, pp.1-19.

[4] P. Turaga, R. Chellappa, V.S. Subrahmanian, O. Udrea, IEEE Transactions on Circuits and Sestems for Video Technology 18 (2008) 1473.

DOI: 10.1109/tcsvt.2008.2005594

[5] S. Zhu, C. Guo, Mathematical modeling of clutter: descriptive vs. generative models, Proceedings of the SPIE AeroSence Conference on Automatic Target Recognition, (2000).

DOI: 10.1117/12.395577

[6] C. Stauffer, W.E.L. Grimson, Adaptive background mixture models for real-time tracking, in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 1999, pp.246-252.

DOI: 10.1109/cvpr.1999.784637

[7] Wren, R. Christopher, A. Azarbayejani, T. Darrell and A, Pentland, Pfinder: real-time tracking of the human body, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7), pp.780-785.

DOI: 10.1109/34.598236

[8] S. Zhang, H. Yao, S. Liu, Dynamic background modeling and subtraction using spatio-temporal local binary patterns, in: Proceedings of IEEE Conference on Image Process, ICIP 2008, pp.1556-1559.

DOI: 10.1109/icip.2008.4712065

[9] C. Ridder, O. Munkelt, H. Kirchner, Adaptive background estimation and foreground detection using Kalman-filtering, in: Proceeings of International Conference on Recent Advances in Mechatronics, 1995, pp.193-199.

[10] B. Langmann, S.E. Ghobadi, K. Hartmann, O. Loffeld, Multi-modal background subtraction using Gaussian mixture models, vol. VIII, part 3A, Saint-Mandé, France, 2010, pp.61-66.

[11] M. Sivabalakrishnan, D. Manjula, Adaptive background subtraction in dynamic environments using Fuzzy logic, in: International Journal of Video & Image process, IJVIPNS-IJENS, vol: 10 No: 01, pp.18-21.

[12] Y.T. Chen, C.S. Chen, C.R. Huang, Y.P. Hung, Efficient hierarchical method for background subtraction, in: Proceeding of Elsevier on Pattern Recognition, 2006, pp.1-10.

[13] T. Matsuyama, T. Ohaya, H. Habe, Background subtraction for non-stationary scenes, in: Proceeding of Asian Conference on Computer Vision, 2000, pp.662-667.

[14] J. Zhong, S. Sclaroff, Segmenting foreground object from a dynamic textured background via a robust kalman filter, in: Proceeding of International Conference on Computer Vision, 2003, pp.44-50.

DOI: 10.1109/iccv.2003.1238312