Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Gait recognition on the basis of markerless motion tracking and DTW transform

  • Author(s): Adam Switonski 1 ; Tomasz Krzeszowski 2 ; Henryk Josinski 1 ; Bogdan Kwolek 3 ; Konrad Wojciechowski 4
    • View affiliations
  • Source: Volume 7, Issue 5, September 2018, p. 415 – 422
    DOI:  10.1049/iet-bmt.2017.0134 , Print ISSN 2047-4938, Online ISSN 2047-4946
© The Institution of Engineering and Technology
Received 04/07/2017, Accepted 20/12/2017, Revised 29/11/2017, Published 03/01/2018

In this study, a framework for view-invariant gait recognition on the basis of markerless motion tracking and dynamic time warping (DTW) transform is presented. The system consists of a proposed markerless motion capture system as well as introduced classification method of mocap data. The markerless system estimates the three-dimensional locations of skeleton driven joints. Such skeleton-driven point clouds represent poses over time. The authors align point clouds in every pair of frames by calculating the minimal sum of squared distances between the corresponding joints. A point cloud distance measure with temporal context has been utilised in k-nearest neighbours algorithm to compare time instants of motion sequences. To enhance the generalisation of the recognition and to shorten the processing time, for every individual a single multidimensional time series among several multidimensional time series describing the individual's gait is established. The correct classification rate has been determined on the basis of a real dataset of human gait. It contains 230 gait cycles of 22 subjects. The tracking results on the basis of markerless motion capture are referenced to Vicon system, whereas the achieved accuracies of recognition are compared with the ones obtained by DTW that is based on rotational data.

Inspec keywords: time series; learning (artificial intelligence); object tracking; image motion analysis; transforms; image sequences; gait analysis; image classification

Other keywords: markerless motion capture system; view-invariant gait recognition; skeleton-driven point clouds; motion sequences; multidimensional time series; markerless motion tracking; gait recognition; classification method; k-nearest neighbours algorithm; dynamic time warping transform; DTW transform

Subjects: Computer vision and image processing techniques; Integral transforms; Image recognition; Integral transforms; Knowledge engineering techniques

References

    1. 1)
      • 26. Wen, R., Tay, W.-L., Nguyen, B.P., et al: ‘Hand gesture guided robot-assisted surgery based on a direct augmented reality interface’, Comput. Methods Programs Biomed., 2014, 116, (2), pp. 68–80.
    2. 2)
      • 2. Salarian, A., Russmann, H., Vingerhoets, F.J.G., et al: ‘Gait assessment in Parkinson's disease: toward an ambulatory system for long-term monitoring’, IEEE Trans. Biomed. Eng., 2004, 51, (8), pp. 1434–1443.
    3. 3)
      • 7. Balazia, M., Plataniotis, K.N.: ‘Human gait recognition from motion capture data in signature poses’, IET Biometrics, 2017, 6, (2), pp. 129–137.
    4. 4)
      • 13. Liu, Z., Sarkar, S.: ‘Simplest representation yet for gait recognition: averaged silhouette’. Proc. 17th Int. Conf. Pattern Recognition 2004 ICPR 2004, August 2004, vol. 4, pp. 211–214, doi: 10.1109/ICPR.2004.1333741.
    5. 5)
      • 1. Mian, O.S., Schneider, S.A., Schwingenschuh, P., et al: ‘Gait in SWEDDs patients: comparison with Parkinson's disease patients and healthy controls’, Mov. Disorders, 2011, 26, (7), pp. 1266–1273.
    6. 6)
      • 32. Petitjean, F., Ketterlin, A., Gançarski, P.: ‘A global averaging method for dynamic time warping, with applications to clustering’, Pattern Recognit., 2011, 44, (3), pp. 678–693, doi: 10.1016/j.patcog.2010.09.013.
    7. 7)
      • 3. Krzeszowski, T., Przednowek, K., Wiktorowicz, K., et al: ‘Estimation of hurdle clearance parameters using a monocular human motion tracking method’, Comput. Methods Biomech. Biomed. Eng., 2016, 19, (12), pp. 1319–1329, doi: 10.1080/10255842.2016.1139092, PMID: 26838547.
    8. 8)
      • 22. Santosh, K.C., Lamiroy, B., Wendling, L.: ‘DTW-radon-based shape descriptor for pattern recognition’, Int. J. Pattern Recognit. Artif. Intell., 2013, 27, (3), doi: 10.1142/S0218001413500080.
    9. 9)
      • 11. Matovski, D.S., Nixon, M.S., Mahmoodi, S., et al: ‘The effect of time on gait recognition performance’, IEEE Trans. Inf. Forensics Sec., 2012, 7, (2), pp. 543–552, doi: 10.1109/TIFS.2011.2176118.
    10. 10)
      • 16. Ariyanto, G., Nixon, M.S.: ‘Model-based 3d gait biometrics’. Int. Joint Conf. Biometrics (IJCB), October 2011, pp. 1–7, doi: 10.1109/IJCB.2011.6117582.
    11. 11)
      • 30. John, V., Trucco, E., Ivekovic, S.: ‘Markerless human articulated tracking using hierarchical particle swarm optimisation’, Image Vis. Comput., 2010, 28, (11), pp. 1530–1547.
    12. 12)
      • 12. Li, X., Chen, Y.: ‘Gait recognition based on structural gait energy image’, J. Comput. Inf. Syst., 2013, 9, (1), pp. 121–126.
    13. 13)
      • 24. Srivastava, R., Sinha, P.: ‘Hand movements and gestures characterization using quaternion dynamic time warping technique’, IEEE Sens. J., 2016, 16, (5), pp. 1333–1341.
    14. 14)
      • 15. Wang, H., Fan, Y., Fang, B., et al: ‘Generalized linear discriminant analysis based on Euclidean norm for gait recognition’, Int. J. Mach. Learn. Cybern., 2016, doi: 10.1007/s13042-016-0540-0.
    15. 15)
      • 5. Gu, J., Ding, X., Wang, S., et al: ‘Action and gait recognition from recovered 3-d human joints’, Trans. Syst. Man Cybern. B, 2010, 40, (4), pp. 1021–1033, ISSN 1083-4419, doi: 10.1109/TSMCB.2010.2043526.
    16. 16)
      • 8. Benedek, C., Gálai, B., Nagy, B., et al: ‘Lidar-based gait analysis and activity recognition in a 4d surveillance system’, IEEE Trans. Circuits Syst. Video Technol., 2016, 28, (1), pp. 102–113.
    17. 17)
      • 18. Balazia, M., Sojka, P.: ‘Gait recognition from motion capture data’. ACM Trans. Multimedia Comput. Commun. Appl., special issue on representation Anal. Recognit. 3D Hum., 2018, 14, (1).
    18. 18)
      • 28. Harvey, F.G., Pal, C.: ‘Semi-supervised learning with encoder-decoder recurrent neural networks: experiments with motion capture sequences’. CoRR, abs/1511.06653, 2015.
    19. 19)
      • 19. Krzeszowski, T., Switonski, A., Kwolek, B., et al: ‘DTW-based gait recognition from recovered 3-d joint angles and inter-ankle distance’. inChmielewski, L.J., Kozera, R., Shin, B.-S., et al (Eds.): ‘Computer vision and graphics’, vol. 8671 (Springer, Cham, 2014), pp. 356–363, ISBN 978-3-319-11330-2, doi: 10.1007/978-3-319-11331-9_43.
    20. 20)
      • 10. Kwolek, B., Krzeszowski, T., Michalczuk, A., et al: ‘3D Gait Recognition Using Spatio-Temporal Motion Descriptors’, 2014 (LNCS, 8398), pp. 595–604, doi: 10.1007/978-3-319-05458-2_61.
    21. 21)
      • 9. Castro, F.M., Marín-Jiménez, M.J., Mata, N.G., et al: ‘Fisher motion descriptor for multiview gait recognition’, Int. J. Pattern Recognit. Artif. Intell., 2017, 31, (01), p. 1756002, doi: 10.1142/S021800141756002X.
    22. 22)
      • 31. Kwolek, B., Krzeszowski, T., Gagalowicz, A., et al: ‘Real-time multi-view human motion tracking using particle swarm optimization with resampling’. inPerales, F.J., Fisher, R.B., Moeslund, T.B. (Eds.): ‘Articulated motion and deformable objects’, vol. 7378 (Springer, Berlin, 2012), pp. 92–101, doi: 10.1007/978-3-642-31567-1_9.
    23. 23)
      • 29. Kovar, L., Gleicher, M.: ‘Flexible automatic motion blending with registration curves’. Proc. 2003 ACM SIGGRAPH/Eurographics Symp. Computer Animation, 2003, pp. 214–224.
    24. 24)
      • 25. Raheja, J.L., Minhas, M., Prashanth, D., et al: ‘Robust gesture recognition using kinect: a comparison between DTW and HMM’, Optik-Int. J. Light Electron Opt., 2015, 126, (11), pp. 1098–1104.
    25. 25)
      • 27. Fragkiadaki, K., Levine, S., Felsen, P., et al: ‘Recurrent network models for human dynamics’. Proc. IEEE Int. Conf. Computer Vision, 2015, pp. 4346–4354.
    26. 26)
      • 21. Ibañez, R., Soria, Á., Teyseyre, A., et al: ‘Easygesture recognition for kinect’, Adv. Eng. Softw., 2014, 76, pp. 171–180.
    27. 27)
      • 17. Zifchock, R.A., Davis, I., Higginson, J., et al: ‘The symmetry angle: a novel, robust method of quantifying asymmetry’, Gait Posture, 2008, 27, (4), pp. 622–627.
    28. 28)
      • 23. Margarito, J., Helaoui, R., Bianchi, A.M., et al: ‘User-independent recognition of sports activities from a single wristworn accelerometer: a template-matching-based approach’, IEEE Trans. Biomed. Eng., 2016, 63, (4), pp. 788–796.
    29. 29)
      • 14. Man, J., Bhanu, B.: ‘Individual recognition using gait energy image’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (2), pp. 316–322, doi: 10.1109/TPAMI.2006.38.
    30. 30)
      • 4. Du, Y., Wang, W., Wang, L.: ‘Hierarchical recurrent neural network for skeleton based action recognition’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2015, pp. 1110–1118.
    31. 31)
      • 20. Switonski, A., Josinski, H., Zghidi, H., et al: ‘Motion data classification on the basis of dynamic time warping with a cloud point distance measure’. Proc. Int. Conf. Numerical Analysis and Applied Mathematics, 2016, vol. 1738, p. 180019, AIP Publishing.
    32. 32)
      • 6. Hachaj, T., Ogiela, M.R., Koptyra, K.: ‘Human actions recognition from motion capture recordings using signal resampling and pattern recognition methods’, Ann. Oper. Res., 2016, pp. 1–17, https://doi.org/10.1007/s10479-016-2308-z.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2017.0134
Loading

Related content

content/journals/10.1049/iet-bmt.2017.0134
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address