Abstract
This paper proposes a statistical background modeling framework to deal with the issue of target detection, where the global and local information is utilized to achieve more accurate detection of moving objects. Specifically, for the target detection problem under illumination change conditions, a novel self-adaptive Gaussian mixture model mixed with the global information is utilized to construct a statistical background model to detect moving objects; for the target detection problem under dynamic background conditions, the self-tuning spectral clustering method is first utilized to cluster background images, and then the kernel density estimation method mixed with the local information is utilized to construct a statistical background model to detect moving objects. Experimental results demonstrate that the proposed framework can improve the detection performance under illumination change conditions or dynamic background conditions.
This is a preview of subscription content, log in via an institution to check access.
References
Bouwmans T, Baf F, Vachon B (2008) Background modeling using mixture of Gaussian for foreground detection: a survey. Recent Patents Comput Sci 1(3):219–237
Elhabian S, Sayed K, Ahmed A (2008) Moving object detection in spatial domain using background removal techniques. Recent Patents Comput Sci 1(1):32–54
Piccardi M (2004) Background subtraction techniques: a review. In: IEEE conference on systems, man, and cybernetics, pp 3099–3104
Radke R, Andra S, Al-Kofahi O, Roysam B (2005) Image change detection algorithms: a systematic survey. IEEE Trans Image Process 14(3):294–307
Wren C, Azarbayejani A, Darrell T, Pentland A (1997) Pfinder: real-time tracking of the human body. IEEE Trans Pattern Anal Mach Intell 19(7):780–785
Friedman N, Russell S (1997) Image segmentation in video sequences: a probabilistic approach. In: IEEE conference on uncertainty in artificial intelligence, pp 175–181
Stauffer C, Grimson W (1999) Adaptive background mixture models for real-time tracking. In: Proc. IEEE conference on computer vision and pattern recognition, pp 246–252
Stauffer C, Grimson W (2000) Learning patterns of activity using real-time tracking. IEEE Trans Pattern Anal Mach Intell 22(8):747–757
Vosters L, Shan C, Gritti T (2010) Background subtraction under sudden illumination changes. In: IEEE conference on advanced video and signal based surveillance, pp 384–391
Glazer A, Lindenbaum M, Markovitch S (2013) One-class background model. Asian conference on computer vision, pp 301–307
Maddalena L, Petrosino A (2008) A self-organizing approach to background subtraction for visual surveillance applications. IEEE Trans Image Process 17(7):1168–1177
Singh Y, Gupta P, Yadav V (2010) Implementation of a self-organising approach to background subtraction for visual surveillance approach. Comput Sci Netw Secur 10(3):136–143
Pilet J, Strecha C, Fua P (2008) Making background subtraction robust to sudden illumination changes. In: European conference on computer vision, pp 567–580
Withagen P, Schutte K, Groen F (2010) Global intensity correction in dynamic scenes. Int J Comput Vis 86(1):33–47
Yoshinaga S, Shimada A, Nagahara H, Taniguchi R (2011) Statistical local difference pattern for background modeling. IPSJ Trans Comput Vis Appl 3(4):198–210
Yoshinaga S, Shimada A, Nagahara H, Taniguchi R (2012) Background model based on statistical local difference pattern. In: Asian conference on computer vision, pp 327–332
Koppal S, Narasimhan S (2009) Appearance derivatives for isonormal clustering of scienes. IEEE Trans Pattern Anal Mach Intell 31(8):1375–1385
Chen Z, Ellis T (2014) A self-adaptive Gaussian mixture model. Comput Vis Image Underst 122(1):35–46
Yoshinaga S, Shimada A (2014) Hajime Nagahara, Rin-ichiro Taniguchi. Object detection based on spatiotemporal background models. Comput Vis Image Underst 122(1):84–91
Acknowledgments
This work was supported by the Postdoctoral Foundation of China under No. 2014M550297, Postdoctoral Foundation of Jiangsu Province under No. 1302087B, Education Reform Research and Practice Program of Jiangsu Province under No. JGZZ13_041, and Graduate Research and Innovation Program of Jiangsu under No. KYLX_0820 and No. SJ22-0106.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, X., Zhu, S. & Chen, L. Statistical background model-based target detection. Pattern Anal Applic 19, 783–791 (2016). https://doi.org/10.1007/s10044-015-0495-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-015-0495-x