Abstract
Conventional background subtraction techniques that update a background model online have difficulties with correctly segmenting foreground objects if sudden brightness changes occur. Other methods that learn a global scene model offline suffer from projection errors. To overcome these problems, we present a different approach that is local and discriminative, i.e. for each pixel a classifier is trained to decide whether the pixel belongs to the background or foreground. Such a model requires significantly less tuning effort and shows a better robustness, as we will demonstrate in quantitative experiments on self-created and standard benchmarks. Finally, segmentation is improved significantly by integrating the probabilistic evidence provided by the local classifiers with a graph cut segmentation algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Boykov, Y., Kolmogorov, V.: An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision. IEEE PAMI 26(9), 1124–1137 (2004)
Duda, R., Hart, P., Stork, D.: Pattern Classification, 2nd edn. Wiley Interscience Publications, Chichester (2000)
Culibrk, D., Marques, O., Socek, D., Kalva, H., Furht, B.: Neural Network Approach to Background Modeling for Video Object Segmentation. IEEE Trans. Neur. Netw. 18(6), 1614–1627 (2007)
Yin, P., Criminisi, A., Winn, J.M., Essa, I.A.: Tree-based Classifiers for Bilayer Video Segmentation. In: CVPR 2007, pp. 1–8 (2007)
Grabner, H., Roth, P.M., Grabner, M., Bischof, H.: Autonomous Learning a Robust Background Model for Change Detection. In: Int. Workshop Perf. Eval. Track. Surv, pp. 39–46 (2006)
Cheung, S., Kamath, C.: Robust Background Subtraction with Foreground Validation for Urban Traffic Video. In: EURASIP Appl. Sign. Proc, pp. 2330–2340 (2005)
Li, L., Huang, W., Gu, I., Tian, Q.: Foreground Object Detection in Changing Background Based on Color Co-Occurrence Statistics. In: WACV 2002, pp. 269–274 (2002)
Noriega, P., Bernier, O.: Real Time Illumination Invariant Background Subtraction Using Local Kernel Histograms. In: BMVC 2006, vol. III, pp. 979–988 (2006)
Piccardi, M.: Background Subtraction Techniques: A Review. IEEE SMC/ICSMC 4, 3099–3104 (2004)
Han, B., Comaniciu, D., Davis, L.: Sequential Kernel Density Approximation through Mode Propagation: Applications to Background Modeling. In: ACCV 2004 (2000)
Elgammal, A.M., Harwood, D., Davis, L.S.: Non-parametric Model for Background Subtraction. In: ECCV 2000, pp. 751–767 (2000)
Wren, C.R., Azarbayejani, A., Darrell, T., Pentland, A.: Pfinder: Real-Time Tracking of the Human Body. IEEE PAMI 19(7), 780–785 (1997)
Horprasert, T., Harwood, D., Davis, L.S.: A Statistical Approach for Realtime Robust Background Subtraction and Shadow Detection. In: IEEE Framerate Workshop, pp. 1–19 (1999)
Oliver, N., Rosario, B., Pentland, A.: A Bayesian Computer Vision System for Modelling Human Interactions. IEEE PAMI 22(8), 831–843 (2000)
Stauffer, C., Grimson, E.: Learning Patterns of Activity Using Real-Time Tracking. IEEE PAMI 22(8), 747–757 (2000)
Sun, J., Zhang, W., Tang, X., Shum, H.-Y.: Background Cut. In: ECCV 2006, pp. 628–641 (2006)
Li, L., Huang, W., Gu, I., Tian, Q.: Statistical Modelling of Complex Backgrounds for Foreground Object Detection. IEEE PAMI 13(11), 75–104 (2004)
Toyama, K., Krumm, J., Brumitt, B., Meysers, B.: Wallflower: Principles and Practice of Background Maintenance. In: ICCV 1999, pp. 255–261 (1999)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ulges, A., Breuel, T.M. (2008). A Local Discriminative Model for Background Subtraction. In: Rigoll, G. (eds) Pattern Recognition. DAGM 2008. Lecture Notes in Computer Science, vol 5096. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69321-5_51
Download citation
DOI: https://doi.org/10.1007/978-3-540-69321-5_51
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69320-8
Online ISBN: 978-3-540-69321-5
eBook Packages: Computer ScienceComputer Science (R0)