Skip to main content
Springer Nature Link
Log in

Multiprocessor architecture for real-time applications using mean shift clustering

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

Abstract

Data mining and machine learning algorithms deal with large amount of data, which with the invention of cost-efficient devices has increased by massive amounts. Many algorithms of these domains are not part of real-time systems because of their computational complexity and large data on which they need to work. A lot of algorithms are being implemented on parallel processing systems like GPUs and FPGAs to achieve the desired speed. The purpose of this article is to provide parallel processing model of mean shift clustering algorithm, targeted to run on FPGA. The general model consists of multiple homogeneous processing entities (PEs) connected through a bus. These PEs work in collaborative working environment with each PE working independently and also communicating with its peers according to the requirements of algorithms. The proposed architecture is implemented on FPGA for one-dimensional data. The algorithm is tested on 99 images from segmentation evaluation database for different number of PEs and different number of fractional bits used to represent mean. The simplicity of algorithm resulted in utilizing only 10.31% of total device slice registers and 33% of total slice LUTs of Spartan 6 FPGA. The processing requirements for the proposed algorithm show that it can be used in real-time systems.

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
$34.99 /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 excludes VAT (USA)
Tax calculation will be finalised during checkout.

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

Similar content being viewed by others

References

  1. Jain, A.K., Murty, M.N., Flynn, P.J.: Data clustering: a review. ACM Comput. Surv. (CSUR) 31(3), 264–323 (1999)

    Article  Google Scholar 

  2. Jain, K.A.: Data clustering: 50 years beyond k-means. Pattern Recognit. Lett. 31(8), 651–666 (2010)

    Article  Google Scholar 

  3. Fukunaga, K., Hostetler, L.D.: The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans. Inf. Theory 21(1), 32–40 (1975)

    Article  MathSciNet  MATH  Google Scholar 

  4. Cheng, Y.: Mean shift, mode seeking, and clustering. IEEE Trans. Pattern Anal. Mach. Intell. 17(8), 790–799 (1995)

    Article  Google Scholar 

  5. Ai, L., Gao, X., Xiong, J.: Application of mean-shift clustering to blood oxygen level dependent functional mri activation detection. BMC Med. Imaging 14(1), 1 (2014)

    Article  Google Scholar 

  6. Filippone, M., Camastra, F., Masulli, F., Rovetta, S.: A survey of kernel and spectral methods for clustering. Pattern Recognit. 41(1), 176–190 (2008)

    Article  MATH  Google Scholar 

  7. Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Trans. Pattern Anal. Mach. Intell. 25(5), 564–577 (2003)

    Article  Google Scholar 

  8. Leichter, I., Lindenbaum, M., Rivlin, E.: Mean shift tracking with multiple reference color histograms. Comput. Vis. Image Underst. 114(3), 400–408 (2010)

    Article  Google Scholar 

  9. Ju, M.-Y., Ouyang, C.-S., Chang, H.-S.: Mean shift tracking using fuzzy color histogram. In: 2010 International Conference on Machine Learning and Cybernetics (ICMLC), vol. 6, pp. 2904–2908. IEEE (2010)

  10. Bousetouane, F., Dib, L., Snoussi, H.: Improved mean shift integrating texture and color features for robust real time object tracking. Vis. Comput. 29(3), 155–170 (2013)

    Article  Google Scholar 

  11. Simon, J.-L., Diederich, M., Troemel, S.: Applying mean-shift-clustering for 3d object detection in remote sensing data. In: EGU General Assembly Conference Abstracts, vol. 15, pp. 9683 (2013)

  12. Che, S., Li, J., Sheaffer, J.W., Skadron, K., Lach, J.: Accelerating compute-intensive applications with gpus and fpgas. In: Symposium on Application Specific Processors, 2008. SASP 2008, pp. 101–107. IEEE (2008)

  13. James-Roxby, P., Schumacher, P., Ross, C.: A single program multiple data parallel processing platform for fpgas. In: 12th Annual IEEE Symposium on Field-Programmable Custom Computing Machines, 2004. FCCM 2004, pp. 302–303. IEEE (2004)

  14. Bai, P., Fu, C., Cao, M., Han, Y.: Improved mean shift segmentation scheme for medical ultrasound images. In: 2010 4th International Conference on Bioinformatics and Biomedical Engineering (iCBBE), pp 1–4. IEEE (2010)

  15. Yang, Changjiang., Duraiswami, Ramani., Davis, Larry.: Efficient mean-shift tracking via a new similarity measure. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005. CVPR 2005, vol. 1, pp. 176–183. IEEE (2005)

  16. Li, Z., Tang, Q.L., Sang, N.: Improved mean shift algorithm for occlusion pedestrian tracking. Electron. Lett. 44(10), 622–623 (2008)

    Article  Google Scholar 

  17. Ning, J., Zhang, L., Zhang, D., Chunlin, W.: Scale and orientation adaptive mean shift tracking. IET Comput. Vis. 6(1), 52–61 (2012)

    Article  MathSciNet  Google Scholar 

  18. Ning, J., Zhang, L., Zhang, D., Chunlin, W.: Robust mean-shift tracking with corrected background-weighted histogram. IET Comput. Vis. 6(1), 62–69 (2012)

    Article  MathSciNet  Google Scholar 

  19. Wang, H., Zhao, J., Li, H., Wang J.: Parallel clustering algorithms for image processing on multi-core cpus. In: 2008 International Conference on Computer Science and Software Engineering, vol. 3, pp. 450–453. IEEE (2008)

  20. Zhang, J., Luo, S., Liu, X.: Weighted mean shift object tracking implemented on gpu for embedded sustems. In: 2012 International Conference on Control Engineering and Communication Technology (ICCECT), pp. 982–985. IEEE (2012)

  21. Xiao, C., Liu, M.: Efficient mean-shift clustering using gaussian kd-tree. In: Computer Graphics Forum, vol. 29, issue 7, pp 2065–2073. Wiley (2010)

    Article  Google Scholar 

  22. Craciun, S., Wang, G., George, A.D., Lam H.K., Principe, J.C.: A scalable rc architecture for mean-shift clustering. In: 2013 IEEE 24th International Conference on Application-Specific Systems, Architectures and Processors (ASAP), pp. 370–374. IEEE (2013)

  23. Men, L., Huang, M., Gauch, J.: Accelerating mean shift segmentation algorithm on hybrid cpu/gpu platforms. In: Proceedings of 2012 International Workshop on Modern Accelerator Technologies for GIScience (MAT4GIScience’12) (2012)

  24. Sirotković, J., Dujmić, H., Papić, V.: Accelerating mean shift image segmentation with ifgt on massively parallel gpu. In: 2013 36th International Convention on Information & Communication Technology Electronics & Microelectronics (MIPRO), pp. 279–285. IEEE (2013)

  25. Li, P., Xiao, L.: Mean shift parallel tracking on gpu. In: Araujo, H., Mendonça, A.M., Pinho, A. J., Torres, M. I. (eds.) Pattern Recognition and Image Analysis, pp. 120–127. Springer, New York (2009)

    Chapter  Google Scholar 

  26. Ali, U., Malik, M.B., Munawar, K.: Fpga/soft-processor based real-time object tracking system. In: 5th Southern Conference on Programmable Logic, 2009. SPL, pp. 33–37. IEEE (2009)

  27. Craciun, S., Kirchgessner, R., George, A.D., Lam, H., Principe, J.C.: A real-time, power-efficient architecture for mean-shift image segmentation. J. Real Time Image Process. 9, 1–16 (2014)

    Article  Google Scholar 

  28. Trieu, D.B.K., Maruyama, T.: An implementation of the mean shift filter on fpga. In: 2011 International Conference on Field Programmable Logic and Applications (FPL), pp. 219–224. IEEE (2011)

  29. Trieu, D.B.K., Maruyama, T.: Real-time color image segmentation based on mean shift algorithm using an fpga. J. Real Time Image Process. 10(2), 345–356 (2015)

    Article  Google Scholar 

  30. Mazur, K., Kryjak, T.: An embedded vision-based tracking system for autonomous robot navigation. Meas. Autom. Monit. 62(5), 172–174 (2016)

    Google Scholar 

  31. Li, L., Huang, H., Qian, B., Lian, J., Zhou, Y.: Vehicle detection method based on mean shift clustering. J. Intell. Fuzzy Syst. 31(3), 1355–1363 (2016)

    Article  Google Scholar 

  32. Rohilla, R., Kapoor, R.: Improved fpga implementation of real time modified mean shift tracking algorithm. Indian J. Sci. Technol. 9(39), 1 (2016)

    Article  Google Scholar 

  33. Usman, A., Mohammad, B.M.: Hardware/software co-design of a real-time kernel based tracking system. J. Syst. Arch. 56(8), 317–326 (2010)

    Article  Google Scholar 

  34. Khan, Z.H., Gu, I.Y.-H., Backhouse, A.G.: Robust visual object tracking using multi-mode anisotropic mean shift and particle filters. IEEE Trans. Circuits Syst. Video Technol. 21(1), 74–87 (2011)

    Article  Google Scholar 

  35. Jiang, J., Teichert, A., Eisner, J., Daume, H.: Learned prioritization for trading off accuracy and speed. In: Advances in Neural Information Processing Systems (NIPS), pp. 1331–1339 (2012)

  36. Alpert, S., Galun, M., Basri, R., Brandt, A.: Image segmentation by probabilistic bottom-up aggregation and cue integration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June (2007)

  37. Khawaja, S.G., Akram, M.U., Khan, S.A., Shaukat, A., Rehman, S.: Network-on-chip based mpsoc architecture for k-mean clustering algorithm. Microprocess. Microsyst. 46, 1–10 (2016)

    Article  Google Scholar 

  38. Khawaja, S.G., Tehreem, A., Akram, M.U., Khan, S.A.: Multicore framework for finding frequent item-sets using tds. In: International Conference on Hybrid Intelligent Systems, pp 340–349. Springer (2016)

  39. Tehreem, A., Khawaja, S.G., Akram, M.U., Khan, S.A., Ali, M.: Parallel architecture for implementation of frequent itemset mining using fp-growth. In 2017 International Conference on Signals and Systems (ICSigSys), pp. 92–98. IEEE (2017)

Download references

Author information

Authors and Affiliations

  1. Department of Computer Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology, Rawalpindi, Pakistan

    Amna Tehreem, Sajid Gul Khawaja, Asad Mansoor Khan, Muhammad Usman Akram & Shoab A. Khan

Authors
  1. Amna Tehreem
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Sajid Gul Khawaja
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Asad Mansoor Khan
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Muhammad Usman Akram
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Shoab A. Khan
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Muhammad Usman Akram.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tehreem, A., Khawaja, S.G., Khan, A.M. et al. Multiprocessor architecture for real-time applications using mean shift clustering. J Real-Time Image Proc 16, 2233–2246 (2019). https://doi.org/10.1007/s11554-017-0733-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-017-0733-0

Keywords