Abstract
We propose a new scheme for novelty detection in image sequences capable of handling non-stationary background scenarious, such as waving trees, rain and snow. Novelty detection is the problem of classifying new observations from previous samples, as either novel or belonging to the background class. An adaptive background model, based on a linear PCA model in combination with local, spatial transformations, allows us to robustly model a variety of appearences. An incremental PCA algorithm is used, resulting in a fast and efficient detection algorithm. The system has been successfully applied to a number of different (outdoor) scenarious and compared to other approaches.
This is a preview of subscription content, log in via an institution to check access.
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
Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Trans. Pattern Analysis and Machine Intelligence 23(6), 681–685 (2001)
Dick, A., Brooks, M.J.: Issues in automated visual surveillance. In: International Conference on Digital Image Computing: Techniques and Applications, Sydney, Australia (2003)
Elgammal, A., Harwood, D., Davis, L.S.: Non-parametric model for background subtraction. In: European Conf. Computer Vision, Dublin, Ireland, vol. II, pp. 751–767 (2000)
Hartley, R., Schaffalitzky, F.: Powerfactorization: Affine reconstruction with missing or uncertain data. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC (submitted, 2004)
Monnet, A., Mittal, A., Paragios, N., Ramesh, V.: Background modeling and subtraction of dynamic scenes. In: Int. Conf. Computer Vision, Nice, France, pp. 1305–1312 (2003)
Morita, T., Kanade, T.: A sequential factorization method for recovering shape and motion from image streams. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(8), 858–867 (1997)
Ohta, N.: A statistical approach to background substraction for surveillance systems. In: Int. Conf. Computer Vision, Vancouver, Canada, vol. II, pp. 481–486 (2001)
Ridder, C., Munkelt, O., Kirchner, H.: Adaptive background estimation and foreground detection using kalman filtering. In: Int. Conf. on Recent Advances in Mechatronics, pp. 193–199 (1995)
Soatto, S., Doretto, G., Wu, Y.N.: Dynamic textures. In: Int. Conf. Computer Vision, Vancouver, Canada, vol. II, pp. 439–446 (2001)
Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: Conf. Computer Vision and Pattern Recognition, Fort Collins, USA, vol. II, pp. 246–252 (1999)
Wren, C.R., Azarbayejani, A., Darrell, T., Pentland, A.P.: Pfinder: real-time tracking of the human body. IEEE Trans. Pattern Analysis and Machine Intelligence 19(7), 780–785 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kahl, F., Hartley, R., Hilsenstein, V. (2004). Novelty Detection in Image Sequences with Dynamic Background. In: Comaniciu, D., Mester, R., Kanatani, K., Suter, D. (eds) Statistical Methods in Video Processing. SMVP 2004. Lecture Notes in Computer Science, vol 3247. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30212-4_11
Download citation
DOI: https://doi.org/10.1007/978-3-540-30212-4_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23989-5
Online ISBN: 978-3-540-30212-4
eBook Packages: Springer Book Archive