Skip to main content
SpringerLink
Log in

Real-time color image segmentation based on mean shift algorithm using an FPGA

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

Abstract

Image segmentation is one of the most important tasks in the image processing, and mean shift algorithm is often used for color image segmentation because of its high quality. The computational cost of the mean shift algorithm, however, is high, and it is difficult to realize its real time processing on microprocessors, though many techniques for reducing the cost have been researched. In this paper, we describe an FPGA system for the image segmentation based on the mean shift algorithm. In the image segmentation based on the mean shift algorithm, the image is once over-segmented, and then the small regions are merged considering the similarity between the over-segmented regions to obtain better segmentation. In our system, the mean shift filter is accelerated using a cache memory which can access to all pixels in a w s × w s pixel window at arbitrary position. This cache memory allows us to process w s × w s pixels in parallel every clock cycle. The region merging is also accelerated by not strictly managing the list structures used for the merging. This loose management causes the redundant and out-of-date data into the list structures, but it makes the pointer dereferences unnecessary, and the overhead by those data can be hidden by pipeline processing. The performance for 768 × 512 pixel images is fast enough for real-time applications.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

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

Similar content being viewed by others

References

  1. Ma, W., Manjunath, B.: Edge flow: a framework of boundary detection and image segmentation. Comput. Vis. Pattern Recognit., 744–749 (1997)

  2. Shi, J., Malik, J.: Normalized cuts and image segmentation. Comput. Vis. Pattern Recognit., 731–737 (1997)

  3. Zhu, S., Yuille, A.: Region competition: unifying snakes,region growing, and bayes/mdl for multiband image segmentation. Pattern Anal. Mach. Intell. 18(9), 884–900 (2002)

    Google Scholar 

  4. Beucher, S., Meyer, F.: The morphological approach to segmentation: the watershed transformation. Mathematical Morphology in Image Processing, Marcel Dekker Inc, New York, pp. 433–481 (1993)

  5. Appiah, K., Hunter, A., Dickinson, P., Meng, H.: Accelerated hardware video object segmentation: from foreground detection to connected components labeling. Comput. Vis. Image Underst. 114(11), 1282–1291 (2010)

    Google Scholar 

  6. Dillinger, P., Vogelbruch, J., Leinen, J., Suslov, S., Patzak, R., Winkler, H., Schwan, K.: Fpga-based real-time image segmentation for medical systems and data processing. IEEE Trans. Nucl. Sci. 53(4), 2097–2101 (2010)

    Article  Google Scholar 

  7. Saegusa, T., Maruyama, T.: An fpga implementation of real-time k-means clustering for color images. J. Real Time Image Process. 2(4), 309–318 (2007)

    Article  Google Scholar 

  8. Trieu, D.B.K., Maruyama, T.: Real-time image segmentation based on a parallel and pipelined watershed algorithm. J. Real Time Image Process. 2(4), 319–329 (2007)

    Google Scholar 

  9. Guo, H., Guo, P., Lu, H.: Fast mean shift procedure with new iteration strategy and re-sampling. IEEE International Conference on Systems, Man and Cybernetics, pp. 2385–2389 (2006)

  10. Qian, Z., Zhu, C., Wang, R.: An improved fast mean shift algorithm for segmentation. International Conference on Computer Application and System Modeling, pp. 116–120 (2010)

  11. Bitsakos, K., Fermuller, C., Aloimonos, Y.: An experimental study of color-based segmentation algorithms based on the mean-shift concept. European Conference on Computer Vision, pp. 506–519 (2010)

  12. Li, P., Xiao, L.: Mean shift parallel tracking on GPU. Iberian Conference on Pattern Recognition and Image Analysis, pp. 120–127 (2009)

  13. Ali, U., Malik, M.B.: Hardware/software co-design of a real-time kernel based tracking system. J. Syst. Archit. 56:317–326 (2010)

    Article  Google Scholar 

  14. Schmidt, C., Koch, A.: Fast region labeling on the reconfigurable platform ACE-V. International Conference on Field Programmable Logic and Applications, pp. 1083–1086 (2003)

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

    Article  MATH  MathSciNet  Google Scholar 

  16. Cheng, Y.: Mean shift, mode seeking, and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 8, pp. 790–799 (1995)

  17. Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 603–619 (2002)

  18. Ugarriza, L.G., Saber, E., Vantaram, S.R., Amuso, V., Shaw, M., Bhaskar, R.: Automatic image segmentation by dynamic region growth and multiresolution merging. IEEE Trans. Image Process 18(10), 2275–2288 (2009)

    Google Scholar 

  19. Luo, Q., Khoshgoftaar, T.M.: Efficient image segmentation by mean shift clustering and mdl-guided region merging. International Conference on Tools with Artificial Intelligence, pp. 337–343 (2004)

  20. Stawiaski, J., Decenciere, E.: Region merging via graphcuts. Image Anal. Stereol. 27(1), 39–45 (2008)

    Google Scholar 

  21. http://links.uwaterloo.ca/Repository.html. Accessed 27 June 2007

  22. Bitsakos, K., Fermller, C., Aloimonos, Y.: An experimental study of color-based segmentation algorithms based on the mean-shift concept. ECCV 2010, Lecture Notes in Computer Science, vol. 6312, pp. 506–519 (2010)

Download references

Author information

Authors and Affiliations

  1. Systems and Information Engineering, University of Tsukuba, 1-1-1 Ten-nou-dai, Tsukuba, Ibaraki, 305-8573, Japan

    Dang Ba Khac Trieu & Tsutomu Maruyama

Authors
  1. Dang Ba Khac Trieu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tsutomu Maruyama
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dang Ba Khac Trieu.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Trieu, D.B.K., Maruyama, T. Real-time color image segmentation based on mean shift algorithm using an FPGA. J Real-Time Image Proc 10, 345–356 (2015). https://doi.org/10.1007/s11554-012-0319-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-012-0319-9

Keywords

Search

Navigation