doi:

DOI: 10.3724/SP.J.1249.2016.05511

Journal of Shenzhen University Science and Engineering (深圳大学学报理工版) 2016/33:5 PP.511-516

Adaptive background modeling via incremental non-negative matrix factorization


Abstract:
A method for adaptive background modeling based on the incremental non-negative matrix factorization (INMF) is proposed. INMF is used to update new background models effectively when new data streams arrive. The experimental results show that, compared with non-negative matrix factorization (NMF), INMF not only takes less running time but also can be used to extract better foregrounds.

Key words:applied mathematics,non-negative matrix factorization,background modeling,incremental learning,feature extraction,full rank factorization,foreground extraction

ReleaseDate:2016-09-27 14:21:24



[1] Jeeva S,Sivabalakrishnan M.Survey on background modeling and foreground detection for real time video surveillance[J].Procedia Computer Science,2015,50:566-571.

[2] Bouwmans T.Traditional and recent approaches in background modeling for foreground detection:an overview[J].Computer Science Review,2014,11(12):31-66.

[3] Cristani M,Farenzena M,Bloisi D,et al.Background subtraction for automated multisensory surveillance:a comprehensive review[J].Eurasip Journal on Advances in Signal Processing,2010,43(24):25-31.

[4] Bouwmans T, El-Baf F,Vachon B.Statistical background modeling for foreground detection:a survey[J].Handbook of Pattern Recognition and Computer Vision,2010,4(2):181-199.

[5] Radke R,Andra S,Al-Kofahi O,et al.Image change detection algorithms:a systematic survey[J].IEEE Transactions on Image Processing,2005,14(3):294-307.

[6] Jolliffe I T.Principal component analysis[M].New York, USA:Springer-Verlag,1986.

[7] Lee D,Seung H.Learning the parts of objects by non-negative matrix factorization[J].Nature,1999,401(6755):788-791.

[8] Zhang Xiaoguo, Huang Tiejun,Tian Yonghong,et al.Background-modeling-based adaptive prediction for surveillance video coding[J].IEEE Transactions on Image Processing, 2014,23(2):769-784.

[9] Popa S,Crookes D, Miller P.Hardware acceleration of background modeling in the compressed domain[J].IEEE Transactions on Information Forensics and Security,2013,8(10):1562-1574.

[10] Rodriguez P, Wohlberg B.A Matlab implementation of a fast incremental principal component pursuit algorithm for video background modeling[C]//IEEE International Conference on Image Processing. Paris:IEEE, 2014:3414-3416.

[11] Bucak S,Gunsel B.Incremental subspace learning via non-negative matrix factorization[J].Pattern Recognition,2009,42(5):788-797.

[12] Cao Bin,Shen Dou,Sun Jiantao,et al. Detect and track latent factors with online non-negative matrix factorization[C]//Proceedings of the 20th international joint conference on Artifical intelligence. San Francisco, USA:ACM, 2007:2689-2694.

[13] Lee D,Seung H.Algorithms for non-negative matrix factorization[J].Nips,2010, 32(6):556-562.

[14] PETS Video Database (http://ftp.pets.rdg.ac.uk/).