Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Parallelization strategies for markerless human motion capture

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

Abstract

Markerless motion capture (MMOCAP) is the problem of determining the pose of a person from images captured by one or several cameras simultaneously without using markers on the subject. Evaluation of the solutions is frequently the most time-consuming task, making most of the proposed methods inapplicable in real-time scenarios. This paper presents an efficient approach to parallelize the evaluation of the solutions in CPUs and GPUs. Our proposal is experimentally compared on six sequences of the HumanEva-I dataset using the CMAES algorithm. Multiple algorithm’s configurations were tested to analyze the best trade-off with regard to the accuracy and computing time. The proposed methods obtain speedups of 8\(\times\) in multi-core CPUs, 30\(\times\) in a single GPU and up to 110\(\times\) using 4 GPUs.

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

Similar content being viewed by others

Notes

  1. Detailed information about the MMOCAP implementation, the GPU kernels source code and experimental results is available at: http://www.uco.es/grupos/kdis/wiki/MMOCAP.

References

  1. Multon, F., Kulpa, R., Hoyet, L., Komura, T.: Interactive animation of virtual humans based on motion capture data. J. Vis. Comput. Animat. 20(5–6), 491–500 (2009)

    Google Scholar 

  2. Zhou, H., Huosheng, H.: Human motion tracking for rehabilitation-a survey. Biomed. Signal Process. Control. 3(1), 1–18 (2008)

    Article  Google Scholar 

  3. Moeslund, T.B., Hilton, A., Krüger, V.: A survey of advances in vision-based human motion capture and analysis. Comput. Vis. Image Underst. 104, 90–126 (2006)

    Article  Google Scholar 

  4. Sigal, L., Balan, A.O., Black, M.J.: Humaneva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. Int. J. Comput. Vis. 87, 4–27 (2010)

    Article  Google Scholar 

  5. Isard, M., Blake, A.: Condensation—conditional density propagation for visual tracking. Int. J. Comput. Vis. 29, 5–28 (1998)

    Article  Google Scholar 

  6. Deutscher, J., Reid, I.: Articulated body motion capture by stochastic search. Int. J. Comput. Vis. 61(2), 185–205 (2005)

    Article  Google Scholar 

  7. Corazza, S., Mündermann, L., Chaudhari, A., Demattio, T., Cobelli, C., Andriacchi, T.: A markerless motion capture system to study musculoskeletal biomechanics: visual hull and simulated annealing approach. Ann. Biomed. Eng. 34(6), 1019–1029 (2006)

    Article  Google Scholar 

  8. John, M., Michael I.: Partitioned sampling, articulated objects, and interface-quality hand tracking. In: Proceedings of the 6th European Conference on Computer Vision-Part II, ECCV ’00, pp 3–19. Springer, London (2000)

  9. Jan, B., Florian, E., Michael B.: Evaluation of hierarchical sampling strategies in 3D human pose estimation. In: Proceedings of the 19th British Machine Vision Conference, pp. 1–10 (2008)

  10. Lozano, M., Molina, D., Herrera, F. (eds.): Special issue on scalability of evolutionary algorithms and other metaheuristics for large-scale continuous optimization problems. Soft computing, vol. 15. Springer, Berlin/Heidelberg (2011)

  11. John, V., Trucco, E., Ivekovic, S.: Markerless human articulated tracking using hierarchical particle swarm optimisation. Image Vis. Comput. 28(11), 1530–1547 (2010)

    Article  Google Scholar 

  12. Zhao, X., Liu, Y.: Generative tracking of 3D human motion by hierarchical annealed genetic algorithm. Pattern Recognit. 41(8), 2470–2483 (2008)

    Article  MATH  Google Scholar 

  13. Yeguas-Bolivar, E., Muñnoz-Salinas, R., Medina-Carnicer, R., Carmona-Poyato, A.: Comparing evolutionary algorithms and particle filters for markerless human motion capture. Appl. Soft Comput. 17, 153–166 (2014)

    Article  Google Scholar 

  14. Hansen, N.: The CMA evolution strategy: a comparing review. In: Lozano, J.A., Larranaga, P., Inza, I., Bengoetxea, E., (eds.) Towards a new evolutionary computation. Advances on Estimation of Distribution Algorithms, pp. 75–102. Springer, Berlin (2006)

  15. Kenneth, V., Price, R.M.S., Jouni A.L.: Differential evolution a practical approach to global optimization. In: The Differential Evolution Algorithm, pp. 37–134. Natural Computing Series. Springer, Berlin (2005)

  16. Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings IEEE International Conference on Neural Networks, vol. 4, pp. 1942–1948 (1995)

  17. Chang, I.-C., Lin, S.-Y.: 3D human motion tracking based on a progressive particle filter. Pattern Recognit. 43(10), 3621–3635 (2010)

    Article  MATH  Google Scholar 

  18. Gall, J., Rosenhahn, B., Brox, T., Seidel, H.-P.: Optimization and filtering for human motion capture. Int. J. Comput. Vis. 87(1–2), 75–92 (2010)

    Article  Google Scholar 

  19. Cappozzo, A., Ugo D.C., Alberto L., Lorenzo C.: Human movement analysis using stereophotogrammetry: Part 1: theoretical background. Gait Posture. 21(2), 186–196 (2005)

    Google Scholar 

  20. Chiari, L., Ugo D.C., Alberto L., Aurelio C.: Human movement analysis using stereophotogrammetry: Part 2: Instrumental errors. Gait Posture. 21(2), 197–211 (2005)

    Article  Google Scholar 

  21. Ugo, D.C, Alberto, L., Lorenzo, C., Aurelio, C.: Alberto Leardini, Lorenzo Chiari, and Aurelio Cappozzo. Human movement analysis using stereophotogrammetry: Part 4: assessment of anatomical landmark misplacement and its effects on joint kinematics. Gait Posture. 21(2), 226–237 (2005)

    Article  Google Scholar 

  22. Leardini, A., Chiari, L., Ugo D.C., Aurelio C.: Human movement analysis using stereophotogrammetry: Part 3. soft tissue artifact assessment and compensation. Gait Posture. 21(2), 212–225 (2005)

    Article  Google Scholar 

  23. Chitty, D.M.: Fast parallel genetic programming: Multi-core cpu versus many-core gpu. Soft Comput. 16(10), 1795–1814 (2012)

    Article  Google Scholar 

  24. Creel, M., Goffe, W.L.: Multi-core CPUs, clusters, and grid computing: a tutorial. Comput. Eco. 32(4), 353–382 (2008)

    Article  MATH  Google Scholar 

  25. 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 Dist. Comput. 68(10), 1370–1380 (2008)

    Article  Google Scholar 

  26. Owens, J.D., Luebke, D., Govindaraju, N., Harris, M., Krger, J., Lefohn, A.E., Purcell, T.J.: A survey of general-purpose computation on graphics hardware. Comput. Gr. Forum 26(1), 80–113 (2007)

    Article  Google Scholar 

  27. NVIDIA Corporation. NVIDIA CUDA Programming and Best Practices Guide. http://www.nvidia.com/cuda (2014)

  28. Rymut, B., Kwolek, B.: GPU-supported object tracking using adaptive appearance models and particle swarm optimization. In: Proceedings of the 2010 international conference on Computer vision and graphics: Part II, ICCVG’10, pp. 227–234 (2010)

  29. Krzeszowski, T., Kwolek, B., Wojciechowski, K.: GPU-accelerated tracking of the motion of 3D articulated figure. Comput. Vis. Gr. pp. 155–162 (2010)

  30. Luca, M., Spela, I., Stefano, C.: Markerless articulated human body tracking from multi-view video with GPU-PSO. In: Gianluca, T., Andy, M.T., Julian F.M., (eds.) Evolvable systems: from biology to hardware, vol. 6274, Lecture Notes in Computer Science, pp. 97–108 (2010)

  31. Rymut, B., Kwolek, B., Krzeszowski, T.: GPU-accelerated human motion tracking using particle filter combined with PSO. Advanced concepts for intelligent vision systems. Lect. Notes Comput. Sci. 8192, pp. 426–437 (2013)

    Article  Google Scholar 

  32. Zhou, Y., Tan, Y.: GPU-based parallel particle swarm optimization. In: IEEE Congress on Evolutionary Computation, pp. 1493–1500 (2009)

  33. Ugolotti, R., Youssef S.G.N., Pablo M., Lvekovi, P., Luca M., Stefano C.: Particle swarm optimization and differential evolution for model-based object detection. Appl. Soft Comput. 13(6), 3092–3105 (2013)

    Article  Google Scholar 

  34. Zheng, Z., Hock, S.S.: Cuda acceleration of 3D dynamic scene reconstruction and 3D motion estimation for motion capture. In: IEEE 18th International Conference on Parallel and Distributed Systems (ICPADS), pp. 284–291 (2012)

  35. Zhang, Z., Hock, S.S, Chee K.Q., Jixiang, S.: GPU-accelerated real-time tracking of full-body motion with multi-layer search. IEEE Trans. Multimed. 15, 106–119 (2013)

    Article  Google Scholar 

  36. Ganapathi, V., Plagemann, C., Koller, D., Thrun, S.: Real time motion capture using a single time-of-flight camera. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 755–762 (2010)

  37. Diaz-Mas, L., Madrid-Cuevas, F.J., Muñoz-Salinas, R., Carmona-Poyato, A., Medina-Carnicer, R.: An octree-based method for shape from inconsistent silhouettes. Pattern Recognit. 45(9), 3245–3255 (2012)

    Article  Google Scholar 

  38. Diaz-Mas, L., Muñoz-Salinas, R., Medina-Carnicer, R., Madrid-Cuevas, F.J.: Shape from silhouette using dempster-shafer theory. Pattern Recognit. 43(6), 2119–2131 (2010)

    Article  MATH  Google Scholar 

  39. Muñoz-Salinas, R., Yeguas-Bolivar, E., Diaz-Mas, L., Medina-Carnicer, R.: Shape from pairwise silhouettes for plan-view map generation. Image Vis. Comput. 30(2), 122–133 (2012)

    Article  Google Scholar 

  40. Horprasert, T., Harwood, D., Davis, L.S.: A statistical approach for real-time robust background subtraction and shadow detection. In: 7th IEEE International Conference on Computer Vision, Frame Rate Workshop (ICCV ’99), pp. 1–19 (1999)

  41. Grégory, R., Carlos O.-U., Martínez-del Rincón, J.: A spatio-temporal 2D-models framework for human pose recovery in monocular sequences. Pattern Recognit. 41, 2926–2944 (2008)

  42. Sundaresan, A., Chellappa, R.: Model driven segmentation of articulating humans in laplacian eigenspace. IEEE Trans. Pattern Anal. Mach. Intell. 30, 1771–1785 (2008)

    Article  Google Scholar 

  43. Zhao, X., Liu, Y.: Generative tracking of 3d human motion by hierarchical annealed genetic algorithm. Pattern Recognit. 41, 2470–2483 (2008)

    Article  MATH  Google Scholar 

  44. Manuel, B., Marc F., Jose C.: Makehuman Team. http://www.makehuman.org/ (2014)

  45. Maeda, T., Yamasaki, T., Aizawa, K.: Model-based analysis and synthesis of time-varying mesh. Lect. Notes Comput. Sci. 5098, 112–121 (2008)

    Article  Google Scholar 

  46. Schmaltz, C., Rosenhahn, B., Brox, T., Weickert, J., Wietzke, L., Sommer, G.: Dealing with self-occlusion in region based motion capture by means of internal regions. Lect. Notes Comput. Sci. 5098, 102–111 (2008)

    Article  Google Scholar 

  47. Shaheen, M., Gall, J., Strzodka, R., Van G.L., Seidel, H.P.: A comparison of 3D model-based tracking approaches for human motion capture in uncontrolled environments. Appl. Comput. Vis. pp. 1–8 (2009)

  48. Demšar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn Res. 7, 1–30 (2006)

    MathSciNet  MATH  Google Scholar 

  49. García, S., Fernández, A., Luengo, J., Herrera, F.: Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: experimental analysis of power. Inf. Sci. 180(10), 2044–2064 (2010)

    Article  Google Scholar 

  50. Kalyanmoy D.: Multi-objective optimization. In: Edmund, K.B., Graham, K., (eds.) Search methodologies, pp. 273–316. Springer, Berlin (2005)

Download references

Acknowledgments

This research was supported by the Spanish Ministry of Science and Technology, projects TIN-2011-22408 and TIN-2012-32952, and by FEDER funds. This research was also supported by the Spanish Ministry of Education under FPU grant AP2010-0042.

Author information

Authors and Affiliations

  1. Department of Computer Science and Numerical Analysis, University of Cordoba, Córdoba, Spain

    Alberto Cano, Enrique Yeguas-Bolivar, Rafael Muñoz-Salinas, Rafael Medina-Carnicer & Sebastián Ventura

  2. Maimonides Institute for Biomedical Research (IMIBIC), Córdoba, Spain

    Enrique Yeguas-Bolivar, Rafael Muñoz-Salinas & Rafael Medina-Carnicer

Authors
  1. Alberto Cano
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Enrique Yeguas-Bolivar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rafael Muñoz-Salinas
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Rafael Medina-Carnicer
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Sebastián Ventura
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rafael Muñoz-Salinas.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Cano, A., Yeguas-Bolivar, E., Muñoz-Salinas, R. et al. Parallelization strategies for markerless human motion capture. J Real-Time Image Proc 14, 453–467 (2018). https://doi.org/10.1007/s11554-014-0467-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-014-0467-1

Keywords

Search

Navigation