A new subspace based solution to background modelling and change detection

Öz

For surveillance system, the background subtraction plays an important role for moving object detection with an algorithm embedded in the camera. Since the existence algorithms cannot satisfy the good accuracy on complex backgrounds including illumination change and dynamic objects, we have put forward the concept of Common Vector Approach (CVA) as a new idea for background modelling. Effectiveness of proposed method is presented through the experiments on popular Wallflower dataset. The obtained visual outputs are compared with well-known methods based on the subjective and objective criteria. From the overall evaluation, we can note the proposed method is not only exhibit successful foreground detection results, but also promises an effective and efficient system for background modelling.

Anahtar Kelimeler

• Common Vector Approach,Background Modelling,Foreground Detection,Moving Object Detection

Kaynakça

1. [1] T. Bouwmans, Subspace learning for background modeling: A survey, Recent Patents on Computer Science, 2 (2009) 223-234.
2. [2] N.M. Oliver, B. Rosario, A.P. Pentland, A bayesian computer vision system for modeling human interactions, Pattern Analysis and Machine Intelligence, IEEE Transactions on, 22 (2000) 831-843.
3. [3] F. De La Torre, M.J. Black, A framework for robust subspace learning, International Journal of Computer Vision, 54 (2003) 117-142.
4. [4] C. Guyon, E.-h. Zahzah, T. Bouwmans, Robust principal component analysis for background subtraction: systematic evaluation and comparative analysis, Citeseer2012.
5. [5] D.-M. Tsai, S.-C. Lai, Independent component analysis-based background subtraction for indoor surveillance, image Processing, IEEE Transactions on, 18 (2009) 158-167.
6. [6] C. Wren, A. Azarbayejani, T. Darrell, A. Pentland, P nder: Real-time tracking of the human body. Media Lab 353, MIT1995.
7. [7] T. Bouwmans, Traditional and recent approaches in background modeling for foreground detection: An overview, Computer Science Review, 11 (2014) 31-66.
8. [8] M.B. Gülmezoğlu, V. Dzhafarov, A. Barkana, The common vector approach and its relation to principal component analysis, Speech and Audio Processing, IEEE Transactions on, 9 (2001) 655-662.

9. [9] Wallflower Dataset, http://research.microsoft.com/en-us/um/people/jckrumm/WallFlower/TestImages.htm.
10. [10] K. Toyama, J. Krumm, B. Brumitt, B. Meyers, Wallflower: Principles and practice of background maintenance, Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on, IEEE1999, pp. 255-261.
11. [11] S. Ergin, M.B. Gulmezoglu, A novel framework for partition-based face recognition, International Journal of Innovative Computing Information and Control, 9 (2013) 1819-1834.
12. [12] S. Gunal, S. Ergin, M.B. Gülmezoğlu, Ö.N. Gerek, On feature extraction for spam e-mail detection, Multimedia content representation, classification and security, Springer2006, pp. 635-642.
13. [13] K. Ozkan, E. Seke, Image denoising using common vector approach, Image Processing, IET, 9 (2015) 709-715.
14. [14] K. Ozkan, S. Isik, A novel multi-scale and multi-expert edge detector based on common vector approach, AEU-International Journal of Electronics and Communications, 69 (2015) 1272-1281.
15. [15] H. Cevikalp, M. Neamtu, M. Wilkes, A. Barkana, Discriminative common vectors for face recognition, IEEE Transactions on pattern analysis and machine intelligence, 27 (2005) 4-13.
16. [16] M. Koc, A. Barkana, O.N. Gerek, A fast method for the implementation of common vector approach, Information Sciences, 180 (2010) 4084-4098.
17. [17] C. Stauffer, W.E.L. Grimson, Adaptive background mixture models for real-time tracking, Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., IEEE1999.
18. [18] A. Elgammal, D. Harwood, L. Davis, Non-parametric model for background subtraction, European conference on computer vision, Springer2000, pp. 751-767.
19. [19] N.M. Oliver, B. Rosario, A.P. Pentland, A bayesian computer vision system for modeling human interactions, IEEE transactions on pattern analysis and machine intelligence, 22 (2000) 831-843.
20. [20] D.-M. Tsai, S.-C. Lai, Independent component analysis-based background subtraction for indoor surveillance, IEEE Transactions on Image Processing, 18 (2009) 158-167.
21. [21] S.S. Bucak, B. Günsel, O. Gursoy, Incremental Non-negative Matrix Factorization for Dynamic Background Modelling, PRIS2007, pp. 107-116.
22. [22] X. Li, W. Hu, Z. Zhang, X. Zhang, Robust foreground segmentation based on two effective background models, Proceedings of the 1st ACM international conference on Multimedia information retrieval, ACM2008, pp. 223-228.