In this work, a new approach to background subtraction based on independent component analysis is presented. This approach assumes that background and foreground information are mixed in a given sequence of images. Then, foreground and background components are identified, if their probability density functions are separable from a mixed space. Afterwards, the components estimation process consists in calculating an unmixed matrix. The estimation of an unmixed matrix is based on a fast ICA algorithm, which is estimated as a Newton-Raphson maximization approach. Next, the motion components are represented by the mid-significant eigenvalues from the unmixed matrix. Finally, the results show the approach capabilities to detect efficiently motion in outdoors and indoors scenarios. The results show that the approach is robust to luminance conditions changes at scene.
References
[1]
Toyama, K.; Krumm, J.; Brumitt, B.; Meyers, B. Wallflower: Principles and Practice of Background Manteinance. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Ft. Collins, CO, USA, June 23–25, 1999; 1, pp. 255–261.
[2]
Horprasert, T.; Harwood, D.; Davis, L.S. A Robust Background Subtraction and Shadow Detection. Proceedings of Asian Conference on Computer Vision, Taipei, Taiwan, February 27–March 3, 2000.
[3]
Stauffer, C.; Grimson, W. Adaptive Background Mixture Models for Real-Time Tracking. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Ft. Collins, CO, USA, June 23–25, 1999; 2, pp. 252–259.
[4]
Cheung, S.C.S.; Kamath, C. Robust Background Subtraction with Foreground Validation for Urban Traffic Video. EURASIP J. Appl. Signal Process？2005, 2005, 2330–2340.
[5]
KaewTraKulPong, P.; Bowden, R. An Improved Adaptive Background Mixture Model for Real-time Tracking with Shadow Detection. Proceedings of the 2nd European Workshop on Advanced Video Based Surveillance Systems, London, UK, September 4, 2001; pp. 149–158.
[6]
Elgammal, A.; Harwood, D.; Davis, L.S. Non-parametric Model for Background Subtraction. Proceedings of IEEE International Conference on Computer Vision, Kerkyra, Corfu, Greece, September 20–25, 1999.
[7]
Oliver, N.M.; Rosario, B.; Pentland, A.P. A Bayesian Computer Vision System for Modeling Human Interactions. IEEE Trans. Pattern Anal. Mach. Intell？2000, 22, 831–843.
[8]
Shaw, P.J.A. Multivariate Statistics for the Environmental Sciences; Hodder-Arnold: London, UK, 2003.
[9]
Rymel, J.; Renno, J.; Greenhill, D.; Orwell, J.; Jones, G. Adaptive Eigen-Backgrounds for Object Detection. Proceedings of IEEE International Conference on Image Processing, Singapore, October 24–27, 2004; 3, pp. 1847–1850.
[10]
Han, B.; Comaniciu, D.; Davis, L. Sequential Kernel Density Approximation through Mode Propagation: Applications to Background Modeling. Proceedings of Asian Conference on Computer Vision, Jeju Island, Korea, January 2004.
[11]
Tang, Z.; Miao, Z. Fast Background Subtraction and Shadow Elimination Using Improved Gaussian Mixture Model. Proceedings of the 6th IEEE International Workshop on Haptic, Audio and Visual Environments and Games, Ottawa, ON, Canada, October 12–14, 2007; pp. 38–41.
[12]
Zhou, D.; Zhang, H.; Ray, N. Texture based Background Subtraction. Proceedings of International Conference on Information and Automation, Zhangjiajie, Hunan, China, June 20–23, 2008; pp. 601–605.
Hyvarinen, A. Survey on Independent Component Analysis. Neural Comput. Surv？1999, 2, 94–128.
[15]
Comon, P. Independent Component Analysis—A New Concept? Signal Process？1994, 36, 287–314.
[16]
Suli, E.; Mayers, D. An Introduction to Numerical Analysis; Cambridge University Press: Cambridge, UK, 2003.
[17]
The University of Reading. Performance Evaluation of Tracking and Surveillance (PETS). Internet, ftp://ftp.pets.rdg.ac.uk/pub/PETS2001/ , 2001. The University of Reading, UK.
[18]
Thirde, D.; Ferryman, J.; Crowley, J.L. Performance Evaluation of Tracking and Surveillance (PETS). Available online: http://pets2006.net/ (accessed on 5 February 2010).
[19]
Kalman, R. A New Approach to Linear Liltering and Prediction Problems. J. Basic Eng？1960, 82, 35–45.
[20]
Dempster, A.; Laird, N.; Rubin, D. Maximum Likelihood from Incomplete Data via the EM Algorithm. JR Statist. Soc？1977, 39, 1–38.
[21]
Hyvainen, A. Fast and Robust Fixed-Point Algorithms for Independent Component Analysis. IEEE Trans. Neural Networks？1999, 10, 626–634.
[22]
Harry, L.; Papadimitrou, C. Elements of the Theory of Computation; Prentice Hall: Upper Saddle River, NJ, USA, 1988.
[23]
Russell, S.; Norvig, P. Artificial Intelligence: A Modern Approach; Prentice Hall: Upper Saddle River, NJ, USA, 2003.
[24]
Salembier, P.; Serra, J. Flat Zones Filtering, Connected Operators and Filters by Reconstruction. IEEE Trans. Image Process？1995, 4, 1153–1160.
[25]
Bao, P.; Zhang, L. Noise Reduction for Multi-scale Resonance Images via Adaptive Multiscale Products Thresholding. IEEE Trans. Med. Imaging？2003, 2, 1089–1099.
[26]
Pless, R.; Larson, J.; Siebers, S.; Westover, B. Evaluation of Local Models of Dynamic Backgrounds. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Madison, WI, USA, June 16–22, 2003; 2, pp. 73–78.
[27]
Herrero, S.; Bescós, J. Background Subtraction Techniques: Systematic Evaluation and Comparative Analysis. In Advanced Concepts for Intelligent Vision Systems; Springer Verlag: Berlin, Germany, 2009.
[28]
Papoulis, A. Probability, Random Variables, and Stochastic Processes; McGraw-Hill: New York, NY, USA, 1991.
