Abstract
This paper proposes a robust method to detect and extract silhouettes of foreground objects from a video sequence of a static camera based on the improved background subtraction technique. The proposed method analyses statistically the pixel history as time series observations. The proposed method presents a robust technique to detect motions based on kernel density estimation. Two consecutive stages of the k-means clustering algorithm are utilized to identify the most reliable background regions and decrease the detection of false positives. Pixel and object based updating mechanism for the background model is presented to cope with challenges like gradual and sudden illumination changes, ghost appearance, non-stationary background objects, and moving objects that remain stable for more than the half of the training period. Experimental results show the efficiency and the robustness of the proposed method to detect and extract the silhouettes of moving objects in outdoor and indoor environments compared with conventional methods.
Similar content being viewed by others
References
L. Wang, W. Hu, and T. Tan: Pattern Recognition 36 (2003) 585.
A. Tavakkoli, M. Nicolescu, G. Bebis, and M. Nicolescu: Mach. Vision Appl. 20 (2009) 395.
W. R. Schwartz, A. Kembhavi, D. Harwood, and L. S. Davis: Proc. IEEE Int. Conf. Computer Vision (ICCV’09), 2009.
K. Kim, T. H. Chalidabhongse, D. Harwood, and L. Davis: Real-Time Imaging 11 (2005) 172.
N. Friedman and S. Russell: Proc. 13th Conf. Uncertainty in Artificial Intelligence (UAI’97), 1997, p. 175.
N. McFarlane and C. Schofield: Mach. Vision Appl. 8 (1995) 187.
C. Ridder, O. Munkelt, and H. Kirchner: Proc. Int. Conf. Recent Advances in Mechatronics, 1995, p. 193.
C. Wren, A. Azarbayejani, T. Darrell, and A. Pentland: IEEE Trans. Pattern Anal. Mach. Intell. 19 (1997) 780.
C. Stauffer and W. Grimson: Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR’99), 1999, p. 246.
W. Grimson, C. Stauffer, R. Romano, and L. Lee: Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR’98), 1998, p. 22.
H. Lin, T. Liu, and J. Chuang: Proc. IEEE Int. Conf. Image Proc. (ICIP’02), 2002, p. 893.
J. Wang, G. Bebis, and R. Mille: IEEE Workshop Object Tracking and Classification Beyond the Visible Spectrum in conjunction with CVPR, 2006.
A. Tavakkoli, M. Nicolescu, and G. Bebis: Proc. 2nd Int. Symp. Visual Computing (ISVC’06), 2006, p. 40.
A. Elgammal, D. Harwood, and L. S. Davis: Proc. 6th European Conf. Computer Vision (ECCV’00), 2000, 2nd ed., p. 751.
P. J. Withagen, K. Schutte, and F. C. Groen: Proc. IEEE Int. Conf. Patt. Recogn. (ICPR’04), 2004, p. 31.
I. Haritaoglu, D. Harwood, and L. Davis: IEEE Trans. Pattern Anal. Mach. Intell. 22 (2000) 809.
J. C. S. Jacques, Jr., C. R. Jung, and S. R. Musse: Proc. 18th Brazilian Symp. Computer Graphics and Image Processing (SIBGRAPI’05), 2005, p. 189.
M. H. Sigari and M. Fathy: Proc. Int. Multi-Conf. Engineers and Computer Scientists, 2008.
R. Cucchiara, C. Grana, M. Piccardi, A. Prati, and S. Sirotti: Proc. Intelligent Transportation Systems Conf., 2001, p. 334.
B. Gloyer, H. Aghajan, K. Siu, and T. Kailath: Proc. SPIE Symp. Electronic Imaging: Image and Video Processing, 1995.
L. Li, W. Huang, I. Gu, and Q. Tian: IEEE Trans. Image Process. 13 (2004) 1459.
Z. Lin, Z. Jiang, and L. S. Davis: Proc. IEEE 12th Int. Conf. Computer Vision (ICCV’09), 2009, p. 444.
M. Trivedi, I. Mikic, and G. Kogut: Proc. IEEE Conf. Intelligent Transportation Systems, 2000, p. 155.
P. D. Z. Varcheie, M. Sills-Lavoie, and G. A. Bilodeau: Sensors 10 (2010) 1041.
K. Toyama, J. Krumm, B. Brumitt, and B. Meyers: Proc. Int. Conf. Computer Vision (ICCV’99), 1999, p. 255.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hamad, A.M., Tsumura, N. Background subtraction based on time-series clustering and statistical modeling. OPT REV 19, 110–120 (2012). https://doi.org/10.1007/s10043-012-0009-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10043-012-0009-7