Skip to main content
SpringerLink
Log in

Real-time GPU color-based segmentation of football players

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

Abstract

In this paper, we propose a multi-camera application capable of processing high resolution images and extracting features based on colors patterns over graphic processing units (GPU). The goal is to work in real time under the uncontrolled environment of a sport event like a football match. Since football players are composed for diverse and complex color patterns, a Gaussian Mixture Models (GMM) is applied as segmentation paradigm, in order to analyze sport live images and video. Optimization techniques have also been applied over the C++ implementation using profiling tools focused on high performance. Time consuming tasks were implemented over NVIDIA’s CUDA platform, and later restructured and enhanced, speeding up the whole process significantly. Our resulting code is around 4–11 times faster on a low cost GPU than a highly optimized C++ version on a central processing unit (CPU) over the same data. Real time has been obtained processing until 64 frames per second. An important conclusion derived from our study is the scalability of the application to the number of cores on the GPU.

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.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Bacon, D., Graham, S.L., Sharp, O.J.: Compiler transformations for high-performance computing. ACM Comput. Surv. 26, 45–420 (1993)

    Google Scholar 

  2. Bayer, B.E.: Bayer. United States Patent num. 3971065 (1975). http://patent.ipexl.com/US/3971065.html

  3. Bilmes, J.: A gentle tutorial of the em algorithm and its application to parameter estimation for gaussian mixture and hidden markov models. Technical report (1998)

  4. Buckley, K., Vaddiraju, A., Perry, R.: A new pruning/merging algorithm for mht multitarget tracking. In: Radar-2000 (2000)

  5. Che, S., Boyer, M., Meng, J., Tarjan, D., Sheaffer, J.W., Skadron, K.: A performance study of general-purpose applications on graphics processors using cuda. J. Parallel Distributed Comput. 68(10), 1370–1380 (2008). ISSN 0743-7315. doi:10.1016/j.jpdc.2008.05.014. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.4849

  6. Chen, T.Q., Lu, Y.: Color image segmentation: an innovate approach. Pattern Recogn. 35, 395–405 (2001)

    Google Scholar 

  7. Cheng, H.D., Sun, Y.: A hierarchical approach to color image segmentation using homogeneity. IEEE Trans. Image Process. 9, 2071–2082 (2000)

    Google Scholar 

  8. NVIDIA Corp. CUDA 2.0 Programming Guide. NVIDIA, 2008. http://www.nvidia.es

  9. Martínez del Rincón, J., Herrero-Jaraba, J.E., Gómez, J.R., Orrite-Uruńuela, C., Medrano, C., Montańés, M.A.: Multi-camera sport player tracking with bayesian estimation of measurements. Comput. Vision Image Understanding (2007)

  10. Martínez del Rincón, J., Orrite Uruńuela, C.: Feature-based human tracking: from coarse to fine. PhD thesis. Zaragoza, University of Zaragoza, Zaragoza, Dic 2008. Presented: December 2008

  11. Fung, J., Mann, S.: Using multiple graphics cards as a general purpose parallel computer: applications to computer vision. In: ICPR ’04: Proceedings of the Pattern Recognition, 17th International Conference on (ICPR’04), vol. 1, pp. 805–808, IEEE Computer Society, Washington, DC, USA (2004). ISBN 0-7695-2128-2. doi:10.1109/ICPR.2004.968

  12. Funk, N.: A study of the kalman filter applied to visual tracking. Technical report, University of Alberta (2003)

  13. Gad, A., Farooq, M., Serdula, J., Peters, D.: Multitarget tracking in a multisensor multiplatform environment. In: The Seventh International Conference on Information Fusion, pp. 206–213, Stockholm, Sweden (2004)

  14. Garland, M., Le Grand, S., Nickolls, J., Anderson, J., Hardwick, J., Morton, S., Phillips, E., Zhang, Y., Volkov, V.: Parallel computing experiences with cuda. Micro, IEEE 28(4), 13–27 (2008). doi:10.1109/MM.2008.57

  15. Gavrila, D., Philonim, V.: Real time object detection for smart vehicles. In: Proceedings of Seventh International Conference on Computer Vision, pp. 87–93 (1999)

  16. Gómez, J.R., Herrero, J.E., Medrano, C., Orrite, C.: Multi-sensor system based on unscented kalman filter. In: Proceedings of Image Processing (VIIP), IASTED International Conference on Visualization, pp. 13–18 (2006)

  17. Software development products Intel® Intel ® VTune Analyzer. Intel Corporation (2009)

  18. Isard, M., Blake, A.: Condensation conditional density propagation for visual tracking. Int. J. Comput. Vision, 29(1), 5–28 (1998). ISSN 0920-5691. doi:10.1023/A:1008078328650

    Google Scholar 

  19. Kumar, N.S.L.P., Satoor, S., Buck, I.: Fast parallel expectation maximization for gaussian mixture models on gpus using cuda. In: 10th IEEE International Conference on High Performance Computing and Communications, pp. 103–109 (2009). doi:10.1109/HPCC.2009.45

  20. Lu, P., Oki, H., Frey, C., Chamitoff, G., Chiao, L., Fincke, E., Foale, C., Magnus, S., McArthur, W., Tani, D., Whitson, P., Williams, J., Meyer, W., Sicker, R., Au, B., Christiansen, M., Schofield, A., Weitz, D.: Orders-of-magnitude performance increases in gpu-accelerated correlation of images from the international space station. J. Real-Time Image Process. (2009). doi:10.1007/s11554-009-0133-1

  21. McLachlan, G.J., Krishnan, T.: The EM Algorithm and Extensions. 2 edn. Wiley Series in Probability and Statistics. Wiley, New York, March 2008. ISBN 0471201707. http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/0471201707

  22. Nguyen, H.: GPU Gems 3. Addison-Wesley, Professional, Reading, August 2007. ISBN 0321515269

  23. Owens, J.D., Houston, M., Luebke, D., Green, S., Stone, J.E., Phillips, J.C.: Gpu computing. In; Proceedings of the IEEE, vol. 96, no. 5, pp. 879–899 (2008). doi:10.1109/JPROC.2008.917757

  24. Owens, J.D., Luebke, D., Govindaraju, N., Harris, M., Krüger, J., Lefohn, A.E., Purcell, T.J.: A survey of general-purpose computation on graphics hardware. Comput. Graphics Forum 26(1), 80–113, March 2007. ISSN 1467-8659. doi:10.1111/j.1467-8659.2007.01012.x

  25. Pérez, P., Hue, C., Vermaak, J., Gangnet, M.: Color-based probabilistic tracking. In: ECCV ’02: Proceedings of the 7th European Conference on Computer Vision-Part I, pp. 661–675, Springer, London (2002). ISBN 3-540-43745-2

  26. Pharr, M., Fernando, R.: GPU Gems 2: Programming Techniques for High-Performance Graphics and General-Purpose Computation. Addison-Wesley Professional, Reading, March 2005. ISBN 0321335597. http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/0321335597

  27. Ryoo, S., Rodrigues, C.I., Baghsorkhi, S.S., Stone, S.S., Kirk, D.B., Hwu, W.W.: Optimization principles and application performance evaluation of a multithreaded gpu using cuda. In: PPoPP ’08: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 73–82. ACM, New York (2008). ISBN 978-1-59593-795-7. doi:10.1145/1345206.1345220

  28. Schneider, S., Yeom, J., Rose, B., Linford, J.C., Sandu, A., Nikolopoulos, D.S.: A comparison of programming models for multiprocessors with explicitly managed memory hierarchies. SIGPLAN Not., 44(4), 131–140 (2009). ISSN 0362-1340. doi:10.1145/1594835.1504197

  29. Sinha, S.N., Frahm, J., Pollefeys, M., Genc, Y.: Gpu-based video feature tracking and matching. Technical report, In: Workshop on Edge Computing Using New Commodity Architectures (2006)

  30. Smith, A.R.: Color gamut transform pairs. In: SIGGRAPH ’78: Proceedings of the 5th Annual Conference on Computer Graphics and Interactive Techniques, pp. 12–19. ACM, New York (1978). doi:10.1145/800248.807361

  31. Tuytelaars, T., Mikolajczyk. K.: Local invariant feature detectors: a survey. Found. Trends. Comput. Graph. Vis. 3(3):177–280 (2008). ISSN 1572-2740. doi:10.1561/0600000017

    Google Scholar 

  32. van der Laan, W.J.: Decuda and cudasm, the cubin utilities package. GIThub (2009)

Download references

Acknowledgments

This work was supported in part by grants TIN2010-21291-C02-01, TIN2007-66423 and TIN2007-60625 (Spanish Government and European ERDF), gaZ: T48 research group (Aragón Government and European ESF), Consolider CSD2007-00050 (Spanish Government), and HiPEAC-2 NoE (European FP7/ICT217068).

Author information

Authors and Affiliations

  1. Maria de Luna, 1, Saragossa, Spain

    Miguel Angel Montañés Laborda, Enrique F. Torres Moreno & José Elías Herrero Jaraba

  2. Penrhyn Road, Kingston Upon Thames, Surrey, KT1 2EE, UK

    Jesús Martínez del Rincón

Authors
  1. Miguel Angel Montañés Laborda
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Enrique F. Torres Moreno
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jesús Martínez del Rincón
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. José Elías Herrero Jaraba
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Miguel Angel Montañés Laborda.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Montañés Laborda, M.A., Torres Moreno, E.F., Martínez del Rincón, J. et al. Real-time GPU color-based segmentation of football players. J Real-Time Image Proc 7, 267–279 (2012). https://doi.org/10.1007/s11554-011-0194-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-011-0194-9

Keywords

Search

Navigation