A ViBe Based Moving Targets Edge Detection Algorithm and Its Parallel Implementation

  • Han ZhangEmail author
  • Yurong Qian
  • Yuefei Wang
  • Renhe Chen
  • Chenwei Tian


In order to improve the computational speed and detection accuracy of the ViBe algorithm in foreground edge detection, an improved algorithm based on ViBe moving objects edge detection is proposed in this study by using the partial neighborhood model H(x, y) of a pixel at the point (x, y) to find the absolute difference between H(x, y) and the pixel’s original background model M(x, y) to determine if the pixel is moving. According to the nature of the algorithm, a method based on offset thread block coordinates to optimize thread divergence is proposed from the perspective of calculation level of kernel function and a CUDA (computing unified device architecture) based method is propsed to optimize the stream transmission between CPU and GPU in order to the run time efficiency of the new algorithm. The experimental results indicated the improved algorithm implements ghost elimination, avoids large-area irrelevant background edges and achieves better efficiency and accuracy.


Parallel computing Graphics processor Unified computing device architecture Moving target edge detection ViBe algorithm Ghost elimination Frame difference method 



  1. 1.
    Jeon, G., Anisetti, M., Lee, J., et al.: Concept of linguistic variable-based fuzzy ensemble approach: application to interlaced HDTV sequences. IEEE Trans. Fuzzy Syst. 17(6), 1245–1258 (2009)CrossRefGoogle Scholar
  2. 2.
    Wu, J., Anisetti, M., Wei, W., et al.: Bayer demosaicking with polynomial interpolation. IEEE Trans. Image Process. 25(11), 5369–5382 (2016)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Wang, J., Wu, J., Wu, Z., et al.: Bayesian method application for color demosaicking. Opt. Eng. 57(5), 1 (2018)Google Scholar
  4. 4.
    Jeon, G., Anisetti, M., Damiani, E., et al.: Locally estimated heterogeneity property and its fuzzy filter application for deinterlacing. Inf. Sci. 354(C), 112–130 (2016)CrossRefGoogle Scholar
  5. 5.
    Shi, J., Wu, J., Anisetti, M., et al.: An interval type-2 fuzzy active contour model for auroral oval segmentation. Soft. Comput. 21(9), 1–21 (2015)Google Scholar
  6. 6.
    Qian, Y., Jeon, G.: Weight assignment using entropy. Int. J. Multimed. Ubiquitous Eng. 11(1), 353–362 (2016)CrossRefGoogle Scholar
  7. 7.
    Qian, Y., Wang, J., Jeon, G., et al.: Image deinterlacing using region-based back propagation artificial neural network. Opt. Eng. 52(6), 3294–3298 (2013)Google Scholar
  8. 8.
    Xie, H., Yuan, B., Xie, W.: Moving target detection algorithm based on the improved three-frame differences and ViBe algorithm. Appl. Sci. Technol. 43(6), 46–52 (2016)Google Scholar
  9. 9.
    Min, W.D., Guo, X.G., Han, Q.: An improved ViBe algorithm and its application in traffic video processing. Guangxue Jingmi Gongcheng/Opt. Precis. Eng. 25(3), 806–811 (2017)Google Scholar
  10. 10.
    Dewes, P., Frellesen, C., Albutmeh, F., et al.: Comparative evaluation of non-contrast CAIPIRINHA-VIBE 3T-MRI and multidetector CT for detection of pulmonary nodules: in vivo evaluation of diagnostic accuracy and image quality. Eur. J. Radiol. 85(1), 193–198 (2016)CrossRefGoogle Scholar
  11. 11.
    Zhang, H.B., Huang, S.: Comprehensive dynamic background updating method for real-time traffic visual surveillance. J. Comput. Appl. 27(9), 2134–2136 (2007)Google Scholar
  12. 12.
    Barnich, O., Van, D.M.: ViBe: a universal background subtraction algorithm for video sequences. IEEE Trans. Image Process. 20(6), 1709–1724 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    章伟明, 周武能.: 基于鬼影判断抑制和局部运动补偿的改进 ViBe 算法. 计算机与现代化.1, 51–55 (2018)Google Scholar
  14. 14.
    于明, 刘帅, 师硕.: 改进的 ViBe 运动目标检测算法. 河北工业大学学报. 46(1), 65–70 (2017)Google Scholar
  15. 15.
    NVIDIA:CUDAcuda parallel computing platform@ONLINE. (2018). Accessed May 2018
  16. 16.
    Wang, P.H., Lo, C.W., Yang, C.L., et al.: A cycle-level SIMT-GPU simulation framework. In: IEEE International Symposium on PERFORMANCE Analysis of Systems and Software. IEEE Computer Society, pp. 114–115 (2012)Google Scholar
  17. 17.
    Goyette, N., Jodoin, P., Porikli, F., et al.: a new change detection benchmark dataset. In: Computer Vision and Pattern Recognition Workshops. IEEE, pp. 1–8 (2012)Google Scholar
  18. 18.
    Wang, J., Han, J., Liu, E., et al.: An improved ViBe moving target detection algorithm. J. Guangxi Univ. (Nat. Sci. Ed.) 6, 2191–2197 (2017)Google Scholar
  19. 19.
    Xie, H., Yuan, B., Xie, W.: A moving target detection algorithm based on improved three-frame difference and ViBe algorithm. J. Appl. Sci. 43(6), 46–52 (2016)Google Scholar
  20. 20.
    He, Z., Huang, S., Yan, G.: A moving target detection algorithm based on improved visual background extraction model. J. Chin. Comput. Syst. 36(11), 2559–2562 (2015)Google Scholar
  21. 21.
    Droogenbroeck, M.V., Paquot, O.: Background subtraction: experiments and improvements for ViBe. In: Computer Vision and Pattern Recognition Workshops. IEEE, pp. 32–37 (2012)Google Scholar
  22. 22.
    Jie, L., Lian, Z., Jia, Y., et al.: No-reference image quality assessment using Prewitt magnitude based on convolutional neural networks. Signal Image Video Process. 10(4), 609–616 (2016)CrossRefGoogle Scholar
  23. 23.
    严红亮,王福龙,刘志煌.: 结合三帧差分的 ViBe 运动检测算法.计算机系统应用. 23(11),105–110 (2014)Google Scholar
  24. 24.
    PETS 2009 Benchmark Data, 2009.
  25. 25.
    Barnich, O., Van Droogenbroeck, M.: ViBe: a powerful random technique to estimate the background in video sequences. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 945–948 (2009)Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of SoftwareXinjiang UniversityÜrümqiChina

Personalised recommendations