An Algorithm of Detecting Moving Foreground Based on an Improved Gaussian Mixture Model

  • Mingjie Wang
  • Jesse S. JinEmail author
  • Xianfeng Han
  • Wei Jiang
  • Yifei Jing
  • Lei Gao
  • Liping Xiao
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 634)


Objective: The technique of detecting moving regions has been playing an important role in computer vision and intelligent surveillance. Gaussian mixture models provide an advanced modeling approach for us. Although this method is very effective, it is not robust when there are some lighting changes and shadows in the scenes. This paper proposes a mixture model based on gradient images. Method: We firstly calculate gradient images of a video stream using the Scharr operator. We then mix RGB and gradient, and use a morphological approach to remove noise and connect moving regions. To further reduce false detection, we make an AND operation between two modeling results and result in final moving regions. Result: Finally, we use three video streams for analysis and comparison. Experiments show that this method has effectively avoided false detection regions resulting from lighting change and shadow, and improves the accuracy of detection. Conclusion: The approach demonstrates its promising characteristics and is more applicable in real-time detection.


GMM (Gaussian mixture Model) Gradient image Scharr operator Sobel Morphological AND operation 


  1. 1.
    Chen, Z., Ellis, T.: A self-adaptive Gaussian mixture model. Comput. Vis. Image Underst. 122, 35–46 (2014)CrossRefGoogle Scholar
  2. 2.
    Yuan, C.F., Wang, C.X., Zhang, X.G., et al.: Video segmentation of illumination abrupt variation based On MOGs and gradient information. J. Image Graph. 12(11), 2068–2070 (2007)Google Scholar
  3. 3.
    Basri, I., Achamad, A.: Gaussian mixture models optimization for counting the numbers of vehicle by adjusting the region of interest under heavy traffic condition. In: International Seminar on Intelligent Technology and Its Applications, 2015 (ISITIA 2015), Surabaya (2015)Google Scholar
  4. 4.
    Qiao, S.J., Jin, K., Han, N., et al.: Trajectory prediction algorithm based on Gaussian mixture model. J. Softw. 26(5), 1048–1049 (2015)MathSciNetGoogle Scholar
  5. 5.
    Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: Computer Vision and Pattern Recognition, 1999 (CVPR 1999), Fort Collins, CO (1999)Google Scholar
  6. 6.
    Cui, W.P., Shen, J.Z.: Moving target detection based on improved Gaussian mixture model. Opto-Electron. Eng. 37(4), 119–121 (2010)Google Scholar
  7. 7.
    Chen, X.Y.: The research and implementation of background modeling and updating algorithm based on mixture gaussian model. Northeastern University, Shenyang (2009)Google Scholar
  8. 8.
    Lei, L.Z.: On the edge detection method of digital image. Bull. Surv. Mapp. 40(3), 40–41 (2006)Google Scholar
  9. 9.
    Lu, Z.Q., Liang, C.: Edge thinning based on Sobel operator. J. Image Graph. 5(6), 516–518 (2000)Google Scholar
  10. 10.
    Yu, S.Q., Liu, R.Z.: Learning OpenCV, pp. 169–171. Tsinghua University Press, BeiJing (2009)Google Scholar
  11. 11.
    Pan, X.H., Zhao, S.G., Liu, Z.P., et al.: Detection of video moving objects by combining grads-based frame difference and background subtraction. Optoelectron. Technol. 29(1), 34–36 (2009)Google Scholar
  12. 12.
    Meng, Y.F., OuYang, N., Mo, J.W., et al.: A shadow removal algorithm with Gaussian mixture model. Comput. Simul. 27(1), 210–212 (2010)Google Scholar
  13. 13.
    Ma, Y.D., Zhu, W.F., An, S.X., et al.: Improved moving objects detection method based on Gaussian mixture model. Comput. Appl. 27(10), 2544–2546 (2007)Google Scholar
  14. 14.
    He, K., Ju, S.G., Lin, T., et al.: Image denoising on TV numerical computation. J. Univ. Electron. Sci. Technol. China 42(3), 459–461 (2013)Google Scholar
  15. 15.
    Gorelick, L., Blank, M., Shechtman, E., et al.: Actions as space-time shapes. IEEE Trans. Pattern Anal. Mach. Intell. 29(12), 2247–2248 (2007)CrossRefGoogle Scholar
  16. 16.
    Fan, W.C., Li, X.Y., Wei, K., et al.: Moving target detection based on improved Gaussian mixture model. Comput. Sci. 42(5), 286–288 (2015)Google Scholar
  17. 17.
    Feng, W.H., Gong, S.R., Liu, C.P.: Foreground detection based on improved Gaussian mixture model. Comput. Eng. 37(19), 179–182 (2011)Google Scholar
  18. 18.
    Sun, D., Liu, J.F., Tang, X.L.: Edge detection based on density gradient. Chin. J. Comput. 32(2), 299–302 (2009)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Singapore 2016

Authors and Affiliations

  • Mingjie Wang
    • 1
  • Jesse S. Jin
    • 1
    • 2
    Email author
  • Xianfeng Han
    • 1
  • Wei Jiang
    • 1
  • Yifei Jing
    • 1
  • Lei Gao
    • 2
  • Liping Xiao
    • 2
  1. 1.School of Computer SoftwareTianjin UniversityTianjinChina
  2. 2.Beijing Aerospace Institute of Automatic ControlBeijingChina

Personalised recommendations