Abstract
Recent evaluation of representative background subtraction techniques demonstrated the drawbacks of these methods, with hardly any approach being able to reach more than 50% precision at recall level higher than 90%. Challenges in realistic environment include illumination change causing complex intensity variation, background motions (trees, waves, etc.) whose magnitude can be greater than the foreground, poor image quality under low light, camouflage etc. Existing methods often handle only part of these challenges; we address all these challenges in a unified framework which makes little specific assumption of the background. We regard the observed image sequence as being made up of the sum of a low-rank background matrix and a sparse outlier matrix and solve the decomposition using the Robust Principal Component Analysis method. We dynamically estimate the support of the foreground regions via a motion saliency estimation step, so as to impose spatial coherence on these regions. Unlike smoothness constraint such as MRF, our method is able to obtain crisply defined foreground regions, and in general, handles large dynamic background motion much better. Extensive experiments on benchmark and additional challenging datasets demonstrate that our method significantly outperforms the state-of-the-art approaches and works effectively on a wide range of complex scenarios.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Barnich, O., Van Droogenbroeck, M.: ViBE: A powerful random technique to estimate the background in video sequences. In: ICASSP (2009)
Brutzer, S., Hoferlin, B., Heidemann, G.: Evaluation of Background Subtraction Techniques for Video Surveillance. In: CVPR (2011)
Bugeau, A., Perez, P.: Detection and segmentation of moving objects in complex scenes. CVIU 113(4), 459–476 (2009)
Candes, E., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? J. ACM 58(3), 1–37 (2011)
Cevher, V., Sankaranarayanan, A., Duarte, F., Reddy, D., Baraniuk, G., Chellappa, R.: Compressive Sensing for Background Subtraction. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 155–168. Springer, Heidelberg (2008)
Eldar, Y.C., Kuppinger, P., Bolcskei, H.: Block-sparse signals: Uncertainty relations and efficient recovery. IEEE Trans. Sig. Proc. 58(6), 3042–3054 (2010)
Elgammal, A., Harwood, D., Davis, L.: Non-parametric Model for Background Subtraction. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 751–767. Springer, Heidelberg (2000)
Fablet, R., Bouthemy, P., Gelgon, M.: A maximality principle applied to a contrario motion detection. In: ICIP (2005)
Huang, J., Huang, X., Metaxas, D.: Learning with dynamic group sparsity. In: ICCV (2009)
Lin, Z., Chen, M., Ma, Y.: The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrix. Arxiv preprint arxiv.org/abs/1009.5055 (2009)
Maddalena, L., Petrosino, A.: A self-organizing approach to background subtraction for visual surveillance applications. Proc. IEEE Trans. Image 17(7), 1168–1177 (2008)
Mittal, A., Paragios, N.: Motion-based background subtraction using adaptative kernel density estimation. In: CVPR (2004)
Qiu, C., Vaswani, N.: ReProCS: a missing link between recursive robust PCA and recursive sparse recovery in large but correlated noise. In: CoRR (2011)
Rosenblum, K., Manor, Z., Eldar, Y.: Dictionary optimization for block-sparse representations. In: AAAI (2010)
Stauffer, C., Grimson, Y.: Adaptive background mixture models for real-time tracking. In: CVPR (1999)
Stojnic, M., Parvaresh, F., Hassibi, B.: On the reconstruction of block-sparse signals with an optimal number of measurements. Proc. IEEE Trans. Sig. 57(8), 3075–3085 (2009)
Sun, D., Roth, S., Black, M.J.: Secrets of optical flow estimation and their principles. In: CVPR (2010)
Tang, G., Nehorai, A.: Robust principal component analysis based on low-rank and block-sparse matrix decomposition. In: CISS (2011)
Wixson, L.: Detecting salient motion by accumulating directionally-consistent flow. PAMI 22(8), 774–780 (2000)
Zhou, X., Yang, C., Yu, W.: Moving object detection by detecting contiguous outliers in the low-Rank representation. Accepted by PAMI (2012)
Zivkovic, Z., van der Heijden, F.: Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognition Letters 27(7), 773–780 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gao, Z., Cheong, LF., Shan, M. (2012). Block-Sparse RPCA for Consistent Foreground Detection. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7576. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33715-4_50
Download citation
DOI: https://doi.org/10.1007/978-3-642-33715-4_50
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33714-7
Online ISBN: 978-3-642-33715-4
eBook Packages: Computer ScienceComputer Science (R0)