Abstract
A motion detection technique is presented which exhibits robust properties suitable for general operation in a surveillance environment. The technique is sensitive to transient perturbations present in an image sequence while being insensitive to temporal clutter. Its performance is robust to scale and offset variations in the input sequence. The system is implemented as a pixel based temporal recursive filter, which requires modest computational resources to process each new input frame. Analysis of filter properties and experimental results for a real image sequence are reported.
Preview
Unable to display preview. Download preview PDF.
References
Karmann, K.-P.; v. Brandt, A.; Gerl, R. 1990. Moving object segmentation based on adaptive reference images. In Torres, L.; Masgrau, E.; Lagunas, M. A., editors, Proceedings, Signal Processing V. theories and applications, (Barcelona, Spain, sep 18–21), Amsterdam. Elsevier, pp. 951–954.
Koller, D.; Weber, J.; Malik, J. 1994. Robust multiple car tracking with occlusion reasoning. In Eklundh, J.-O., editor, Third European Conference on Computer Vision, (Stockholm, Sweden, ay 1994), Volume 1, Berlin. Springer-Verlag, pp. 189–196.
Letang, J. M.; Rebuffel, V.; Bouthemy, P. 1993. Motion detection robust to perturbations: a statistical regularization and temporal integration framework. In Fourth International Conference on Computer Vision (Berlin, Germany, May 11–14, 1993), Washington, DC. Computer-Society Press.
Makarov, A. 1996. Comparison of background extraction based intrusion detection algorithms. In 1996 International Conference on Image Processing, (Lausanne, Switzerland, September 16–19, 1996), Washington, DC. IEEE Signal Processing Society.
Ngan, P. M. 1997. Motion detection in temporal clutter. Technical Report 693, Industrial Research Limited, Auckland, New Zealand.
Oppenheim, A. V.; Schafer, R. W. 1989. Discrete-time signal processing. Signal processing series. Prentice-Hall, Englewood Cliffs, New Jersey.
Ridder,.C.; Munkelt, O.; Kirchner, H. 1995. Adaptive background estimation and foreground detection using kalman-filtering. In Kaynak, O.; Özkan, M.; Bekiroğlu, N.; Tunay, I., editors, Proceedings of International Conference on recent Advances in Mechatronics, ICRAM'95, Boğaziçi University, 80815 Bebek, Istanbul, TURKEY. UNESCO Chair on Mechatronics, pp. 193–199.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ngan, P.M. (1997). Motion detection in temporal clutter. In: Chin, R., Pong, TC. (eds) Computer Vision — ACCV'98. ACCV 1998. Lecture Notes in Computer Science, vol 1352. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63931-4_269
Download citation
DOI: https://doi.org/10.1007/3-540-63931-4_269
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63931-2
Online ISBN: 978-3-540-69670-4
eBook Packages: Springer Book Archive