HMM Based Evaluation of Physical Therapy Movements Using Kinect Tracking

  • Carlos PalmaEmail author
  • Augusto Salazar
  • Francisco Vargas
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9474)


Recognition of human activities in videos has experienced considerable changes with the introduction of cost-effective technology that allows for the tracking of individual body parts. This has led to the development of numerous tele-health applications that aim to help patients in their recovery process. Most of these systems are based on techniques to measure the degree of similarity of time series, together with thresholds to evaluate whether the movement satisfies the specification. This means that sequences similar enough to a template, but containing deviations from the correct form, may be considered correct, and thus the quality of movement incorrectly assessed. In this paper we propose the use of Hidden Markov Models as novelty detectors to evaluate the quality of movement in human beings. The results show the potential of this approach in detecting the sequences that deviate from normality for a wide range of activities common in physical therapy and rehabilitation.



This work was funded by Ruta N (Regalías de la Nación), número del convenio: 512C-2013. Código SUI (Viceinvestigaciones UdeA): 20139080.


  1. 1.
    Ravi, A.: Automatic gesture recognition and tracking system for physiotherapy. In: Electrical Engineering and Computer Sciences University of California at Berkeley (2013)Google Scholar
  2. 2.
    Kayama, H., et al.: Efficacy of an exercise game based on kinect in improving physical performances of fall risk factors in community-dwelling older adults. Games Health: Res. Dev. Clin. Appl. 2(4), 247–252 (2013)CrossRefGoogle Scholar
  3. 3.
    Zhao, W., et al.: Rule based realtime motion assessment for rehabilitation exercises. In: IEEE Symposium on Computational Intelligence in Healthcare and e-health (CICARE 2014), pp. 133–140. IEEE (2014)Google Scholar
  4. 4.
    Zhao, W., et al.: A feasibility study of using a single kinect sensor for rehabilitation exercises monitoring: a rule based approach. In: IEEE Symposium on Computational Intelligence in Healthcare and e-health (CICARE 2014), pp. 1–8. IEEE (2014)Google Scholar
  5. 5.
    Song, Y., et al.: A kinect based gesture recognition algorithm using GMM and HMM. In: 6th International Conference on Biomedical Engineering and Informatics (BMEI 2013), pp. 750–754. IEEE (2013)Google Scholar
  6. 6.
    Godoy, V., et al.: An HMM-based gesture recognition method trained on few samples. In: IEEE 26th International Conference on Tools with Artificial Intelligence (ICTAI 2014), pp. 640–646. IEEE (2014)Google Scholar
  7. 7.
    Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans. Acoust. Speech Signal Process. 26(1), 43–49 (1978)zbMATHCrossRefGoogle Scholar
  8. 8.
    Velloso, E., Bulling, A., Gellersen, H.: MotionMA: motion modelling and analysis by demonstration. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 1309–1318. ACM (2013)Google Scholar
  9. 9.
    Su, C., Huang, J., Huang, S., et al.: Ensuring home-based rehabilitation exercise by using kinect and fuzzified dynamic time warping algorithm. In: Proceedings of the Asia Pacific Industrial Engineering and Management Systems Conference, pp. 884–895 (2012)Google Scholar
  10. 10.
    Cuellar, M.P., Ros, M., Martin-Bautista, M.J., Le Borgne, Y., Bontempi, G.: An approach for the evaluation of human activities in physical therapy scenarios. In: Agüero, R., Zinner, T., Goleva, R., Timm-Giel, A., Tran-Gia, P. (eds.) MONAMI 2014. LNICST, vol. 141, pp. 401–414. Springer, Heidelberg (2015) Google Scholar
  11. 11.
    Staab, R.: Recognizing specific errors in human physical exercise performance with Microsoft Kinect (2014)Google Scholar
  12. 12.
    Velloso, E., et al.: Qualitative activity recognition of weight lifting exercises. In: Proceedings of the 4th Augmented Human International Conference, pp. 116–123. ACM (2013)Google Scholar
  13. 13.
    Paiement, A., et al.: Online quality assessment of human movement from skeleton data. Computing 27(1), 153–166 (2009)Google Scholar
  14. 14.
    Smyth, P.: Markov monitoring with unknown states. IEEE J. Sel. Areas Commun. 12(9), 1600–1612 (1994)CrossRefMathSciNetGoogle Scholar
  15. 15.
    Yan, Z., Chi, D., Deng, C.: An outlier detection method with wavelet HMM for UUV prediction following (2013)Google Scholar
  16. 16.
    Zhu, J., Ge, Z., Song, Z.: HMM-driven robust probabilistic principal component analyzer for dynamic process fault classification. IEEE Trans. Industr. Electron. 62(6), 3814–3821 (2015)Google Scholar
  17. 17.
    Souza, C.R.: The Accord.NET Framework, Decemeber 2014.
  18. 18.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. In: Proceedings of the IEEE 77.2, pp. 257–286 (1989)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Carlos Palma
    • 1
    Email author
  • Augusto Salazar
    • 1
    • 2
  • Francisco Vargas
    • 1
  1. 1.Grupo SISTEMIC, Facultad de IngenieríasUniversidad de Antioquia UdeAMedellínColombia
  2. 2.Grupo de Investigación AEyCC, Facultad de IngenieríasInstituto Tecnológico Metropolitano ITMMedellínColombia

Personalised recommendations