[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

An optimisation of Gaussian mixture models for integer processing units

  • Original Research Paper
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

    We’re sorry, something doesn't seem to be working properly.

    Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Abstract

This paper investigates sub-integer implementations of the adaptive Gaussian mixture model (GMM) for background/foreground segmentation to allow the deployment of the method on low cost/low power processors that lack Floating Point Unit. We propose two novel integer computer arithmetic techniques to update Gaussian parameters. Specifically, the mean value and the variance of each Gaussian are updated by a redefined and generalized “round” operation that emulates the original updating rules for a large set of learning rates. Weights are represented by counters that are updated following stochastic rules to allow a wider range of learning rates and the weight trend is approximated by a line or a staircase. We demonstrate that the memory footprint and computational cost of GMM are significantly reduced, without significantly affecting the performance of background/foreground segmentation.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

References

  1. Apewokin, S., Valentine, B., Forsthoefel, D., Wills, L., Wills, S., Gentile, A.: Embedded real-time surveillance using multimodal mean background modeling. In: Kisaanin, B., Bhattacharyya, SS., Chai, S. (eds.) Embedded Computer Vision, Advances in Pattern Recognition, pp. 163–175. Springer, London (2009)

  2. Ben Tan, L.W.; Junping, Z.: Semi-supervised elastic net for pedestrian counting. Patt. Recogn. (2011)

  3. Candes, E., Romberg, J., Tao, T.: Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. Info. Theory IEEE Trans. 52(2), 489–509 (2006). doi:10.1109/TIT.2005.862083

  4. Cheung, S.C.S., Kamath, C.: Robust techniques for background subtraction in urban traffic video. SPIE, 5308:881–892 (2004). doi:10.1117/12.526886

    Google Scholar 

  5. Cucchiara, R., Grana, C., Piccardi, M., Prati, A.: Detecting moving objects, ghosts, and shadows in video streams. Patt. Anal. Mach. Intell. IEEE Trans. 25(10), 1337–1342 (2003). doi:10.1109/TPAMI.2003.1233909

    Article  Google Scholar 

  6. Debian project Raspbian. http://www.raspbian.org/ (2012)

  7. Donoho, D.: Compressed sensing. Info. Theory IEEE Trans. 52(4),1289–1306 (2006). doi:10.1109/TIT.2006.871582

    Article  MathSciNet  MATH  Google Scholar 

  8. Elia, M., Neri, F.: Generation of pseudorandom independent sequences. In: IASTED International Symposium MIC ’86 (1986)

  9. Hung, M.H., Pan, J.S., Hsieh, C.H.: Speed up temporal median filter for background subtraction. In: Proceedings of the 2010 First International Conference on Pervasive Computing, Signal Processing and Applications, IEEE Computer Society, Washington, DC, USA, PCSPA ’10, pp. 297–300. doi:10.1109/PCSPA.2010.79 (2010)

  10. Hwang, Y., Kim, J.S., Kweon, I.S.: Sensor noise modeling using the skellam distribution: Application to the color edge detection. In: Computer Vision and Pattern Recognition, 2007. CVPR ’07. IEEE Conference on, pp. 1–8. doi:10.1109/CVPR.2007.383004 (2007)

  11. Iannizzotto, G., La Rosa, F., Lo Bello, L.: A wireless sensor network for distributed autonomous traffc monitoring. In: Human System Interactions (HSI), 2010 3rd Conference on, pp. 612–619. doi:10.1109/HSI.2010.5514504 (2010)

  12. Lo, B., Velastin, S.: Automatic congestion detection system for underground platforms. In: Intelligent Multimedia, Video and Speech Processing, 2001. Proceedings of 2001 International Symposium on, pp. 158–161. doi: 10.1109/ISIMP.2001.925356 (2001)

  13. McFarlane, N.J.B., Schofield, C.P.: Segmentation and tracking of piglets in images. Mach. Vision Appl. 8(3), 187–193 (1995). doi:10.1007/BF01215814

    Article  Google Scholar 

  14. Microchip PIC32MX3XX/4XX Family Data Sheet. http://www.microchip.com (2008)

  15. Pagano, P., Salvadori, C., Madeo, S., Petracca, M., Bocchino, S., Alessandrelli, D., Azzar, A., Ghibaudi, M., Pellerano, G., Pelliccia, R.: A middleware of things for supporting distributed vision applications. In: Proceedings of the 1st Workshop on Smart Cameras for Robotic Applications (SCaBot) (2012)

  16. Piccardi, M.: Background subtraction techniques: a review. In: Systems, Man and Cybernetics, 2004 IEEE International Conference on, vol. 4, pp. 3099–3104. doi:10.1109/ICSMC.2004.1400815 (2004)

  17. Radke, R.J., Andra, S., Al-Kofahi, O,, Roysam, B.: Image change detection algorithms: a systematic survey. IEEE Trans. Image Proc. 14:294–307 (2005)

    Article  MathSciNet  Google Scholar 

  18. Rahimi, M., Baer, R., Iroezi, O.I., Garcia, J.C., Warrior, J., Estrin, D., Srivastava, M.: Cyclops: In situ image sensing and interpretation in wireless sensor networks. In: In SenSys, ACM Press, pp. 192–204 (2005)

  19. Raspberry Pi Foundation (2011) Raspberry Pi BOARD. http://www.raspberrypi.org/

  20. Salvadori, C., Makris, D., Petracca, M., del Rincón, J.M., Velastin, S.A.: Gaussian mixture background modelling optimisation for micro-controllers. In: ISVC (1), pp. 241–251 (2012)

  21. Scuola Superiore Sant’Anna and Evidence srl SEED-EYE BOARD. http://www.evidence.eu.com/products/seed-eye.html (2011)

  22. Shen, Y., Hu, W., Liu, J., Yang, M., Wei, B., Chou, C.: Efficient background subtraction for real-time tracking in embedded camera networks. In: Proceedings of the 10th ACM conference on Embedded Network Sensor Systems (2012)

  23. Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., vol 2. doi:10.1109/CVPR.1999.784637 (1999)

  24. Weinland, D., Ronfard, R., Boyer, E.: Free viewpoint action recognition using motion history volumes. Comp Vis Image Understand 104(2–3), 249–257 (2006)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. TeCIP Institute, Scuola Superiore Sant’Anna, via Moruzzi 1, 56124, Pisa, Italy

    Claudio Salvadori

  2. National Inter-University Consortium for Telecommunications, Pisa, Italy

    Matteo Petracca

  3. The Institute of Electronics, Communications and Information Technology (ECIT), Queens University of Belfast, Belfast, UK

    Jesus Martinez del Rincon

  4. Department of Informatic Engineering, Universidad de Santiago de Chile, Santiago de Chile, Chile

    Sergio A. Velastin

  5. Digital Imaging Research Centre, Kingston University, London, UK

    Dimitrios Makris

Authors
  1. Claudio Salvadori
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Matteo Petracca
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jesus Martinez del Rincon
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sergio A. Velastin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Dimitrios Makris
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Claudio Salvadori.

Appendix

Appendix

1.1 Proof from Sect. 3.5.1

A uniformly distributed random number \({\bf X} \in [0, \rm max]\) is characterized by the cumulative distribution function in Eq. 48 and the probability density function in Eq. 49.

$$ F_X(x) = P({\bf X}\leq x) = {{x}\over {\rm max}} $$
(48)
$$ f_X(x) = {{\partial}\over {\partial x}} F_X(x) = 1 $$
(49)

On the other hand, if we consider the value P(X n  > T X ) and we use the probability properties, the following relation can be obtained:

$$ P({\bf X} > T_X) = 1 - F_X(x) = 1 - {{T_X}\over {\rm max}} $$
(50)

From the assumption in Eqs. 38, 39 is true.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Salvadori, C., Petracca, M., del Rincon, J.M. et al. An optimisation of Gaussian mixture models for integer processing units. J Real-Time Image Proc 13, 273–289 (2017). https://doi.org/10.1007/s11554-014-0402-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-014-0402-5

Keywords

Search

Navigation