Advertisement

An Adaptive Thresholding Method for Background Subtraction Based on Model Variation

  • ShaoHu Peng
  • MingJie Deng
  • YuanXin Zhu
  • ChangHong Liu
  • Zhao Yang
  • Xiao Hu
  • Yuan Wu
  • HyunDo NamEmail author
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 516)

Abstract

Background subtraction is an important task in computer vision. Pixel-based methods have a high processing speed and low complexity. But when the video frame with camouflage problem is processed, this kind of methods usually output incomplete foreground. In addition, the parameters of many algorithms are invariable. These methods cannot tackle non-static background. In this paper, we present an adaptive background subtraction algorithm derived from ViBe. Gaussian Kernel template is used to model initialization and update. Standard deviation is used to measure background dynamics. We test our algorithm on a public dataset, named changedetection.net. The results show that we can handle most of scenarios. Compared to ViBe, we achieve better result generally, especially in dynamic background and camera jitter categories.

Keywords

Background subtraction GMM Adaptive thresholding Visual surveillance Computer vision 

Notes

Acknowledgements

This work was supported by Guangdong provincial scientific and technological project (ID: 2017B020210005), Student’s Platform for Innovation and Entrepreneurship Training Program (ID: 201711078010), and the National Natural Science of Foundation of China (No. 61501177).

References

  1. 1.
    Bouwmans T, Maddalena L, Petrosino A. Scene background initialization: a taxonomy. Pattern Recogn Lett. 2017;96:3–11.CrossRefGoogle Scholar
  2. 2.
    Stauffer C, Grimson W. Adaptive background mixture models for real-time tracking. In: IEEE international conference on computer vision and pattern recognition; 1999. p. 246–52.Google Scholar
  3. 3.
    Chen CC, Aggarwal J. An adaptive background model initialization algorithm with objects moving at different depths. In: IEEE international conference on image processing; 2008; p. 2664–7.Google Scholar
  4. 4.
    Bevilacqua A, Stefano LD, Lanza A. An effective multi-stage background generation algorithm. In: IEEE international conference on video and signal based surveillance; 2005. p. 388–93.Google Scholar
  5. 5.
    Farin D, De With PHN, Effelsberg W. Robust background estimation for complex video sequences. In: IEEE international conference on image processing, vol. 1; 2003. p. I-145–8.Google Scholar
  6. 6.
    Lin HH, Liu TL, Chuang JH. Learning a scene background model via classification. IEEE Trans Sig Process. 2009;57(5):1641–54.MathSciNetCrossRefGoogle Scholar
  7. 7.
    Colombrai A, Fusiello A. Patch-based background initialization in heavy cluttered video. IEEE Trans Image Process. 2010;19(4):926–33.MathSciNetCrossRefGoogle Scholar
  8. 8.
    Goyette N et al. Changedetection.net: a new change detection benchmark dataset. In: IEEE international conference on computer vision and pattern recognition workshops (CVPRW); 2012. p. 1–8.Google Scholar
  9. 9.
    Barnich O, Van Droogenbroeck M. ViBe: a universal background subtraction algorithm for video sequences. IEEE Trans Image Process. 2011;20(6):1709–24.MathSciNetCrossRefGoogle Scholar
  10. 10.
    Zivkovic Z. Improved adaptive Gaussian mixture model for background subtraction. In: IEEE international conference on pattern recognition; 2004. p. 28–31.Google Scholar
  11. 11.
    Jodoin J-P, Bilodeau G, Saunier N. Background subtraction based on local shape. Technical report; 2012. arXiv:1204.6326v1.

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • ShaoHu Peng
    • 1
  • MingJie Deng
    • 1
  • YuanXin Zhu
    • 1
  • ChangHong Liu
    • 1
  • Zhao Yang
    • 1
  • Xiao Hu
    • 1
  • Yuan Wu
    • 2
  • HyunDo Nam
    • 3
    Email author
  1. 1.School of Mechanical and Electrical EngineeringGuangzhou Higher Education Mega Center, GuangZhou UniversityGuangZhouChina
  2. 2.B3-4A1 Merchants Guangming Science ParkGuangming District, Shenzhen CityPeople’s Republic of China
  3. 3.Department of Electronics and Electronical EngineeringDankook UniversityYongin-siSouth Korea

Personalised recommendations