Research on Background Modeling Based on Low-Rank Matrix Recovery

Abstract:

Key and difficult points of background subtraction method lie in looking for an ideal background modeling under complex scene. Stacking the individual frames as columns of a big matrix, background parts can be viewed as a low-rank background matrix because of large similarity among individual frames, yet foreground parts can be viewed as a sparse matrix as foreground parts play a small role in individual frames. Thus the process of video background modeling is in fact a process of low-rank matrix recovery. Background modeling based on low-rank matrix recovery can separate foreground images from background at the same time without pre-training samples, besides, the approach is robust to illumination changes. However, there exist some shortcomings in background modeling based on low-rank matrix recovery by analyzing numerical experiments, which is developed from three aspects.

• Periodical: Applied Mechanics and Materials (Volumes 635-637)
• Pages: 1056-1059
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.635-637.1056
• Online since: September 2014
• Authors: Bao Yan Wang, Xin Gang Wang
• Keywords: Background Modeling, Low-Rank Matrix Recovery, Real-Time, Sparse Matrix

References

[1] Ling Guo, Study on Moving Object Detection in Intelligent Video Surveillance (Ph.D., South China University, China, 2013), pp.11-13. (In Chinese).

[2] Yanping Chen, Research on Moving Object Detection Algorithms Based on Background Subtraction (Ph.D., Xiamen University, China, 2008), pp.6-8. (In Chinese).

[3] Candes E J, Li X D, Ma Y, Wright J, Journal of the ACM. Vol. 58 (2011), pp.1-37.

[4] Boyd S, Bandenberghe L, Convex Optimization (Cambridge University Press, UK 2004).

[5] Zuo W, Lin Z. IEEE Transactions on Image Process, Vol. 20 (2011), pp.2748-2759.

[6] JIAN-FENG CAI, EMMANUEL J, CANDES, ZUOWEI SHEN, SIAM J. OPTIM, Vol. 20 (2011), p. (1958).

[7] LIN Z，CHEN M，WU L . et al, The augmented Lagrange multiplier method for exact recovery of a corrupted low-rank matrix (UIUC Technical Report UILU-ENG-09-2215, 2009).

[8] Peng Y G, Ganesh A, Wright J, Xu W L, Ma Y. RASL, In: Proceedings of the 2010 IEEE International Conference on Computer Vision and Pattern Recognition (CVPR). (San Francisco, CA, June 13-18, 2010), pp.763-770.

DOI: 10.1109/cvpr.2010.5540138

[9] Wu L, Ganesh A, Shi B, Matsushita Y, Wang Y T, Ma Y, In: Proceedings of the 10th Asian Conference on Computer Vision, (Berlin, Heidelberg, Springer-Verlag, 2010), pp.703-717.

[10] Xiaohui Shen, Ying Wu, In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (Providence, Rhode Island, U.S. A , June 16-21, 2012).

[11] HUZheng-ping, LI Jing. ACTA ELECTRONICA SINICA. Vol. 41 (2013) No. 5, pp.987-991. (In Chinese).