Semi-automatic, Landmark-Based Feedback Generation for Stand-Up Exercises

  • Pablo Fernández de DiosEmail author
  • Paul Wai Hing Chung
  • Qinggang Meng
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 331)


This paper presents an approach to automatic human motion feedback generation for basic stand-up exercises. A semi-supervised classifier, based on the C4.5 decision tree algorithm and AdaBoost, is trained with ground-truth, manually labelled sequences of key body poses. Before calculating feedback features to be learnt, synchronisation of training and testing sequences –often incomplete and/or asymmetric– with a reference (the tutor or exemplary performance) is done. Finally, an algorithm for adaptation of a performance to that of the tutor is proposed, in order to further enrich the feedback delivered to the user. The proposed framework generates numerical feedback to the user and the main limitations of the proposed approach are discussed.


exercises assessment supervised machine learning feedback 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ben-Horin, B.: Introducing OpenNI (2011), (online; accessed 2012)
  2. 2.
    Bickmore, T.W., Schulman, D., Sidner, C.L.: A reusable framework for health counseling dialogue systems based on a behavioral medicine ontology. Journal of Biomedical Informatics 44(2), 183–197 (2011)CrossRefGoogle Scholar
  3. 3.
    Blanchard, E., Chalfoun, P., Frasson, C.: Towards advanced learner modeling: discussions on quasi real-time adaptation with physiological data. In: Seventh IEEE International Conference on Advanced Learning Technologies (ICALT), pp. 809–813 (2007)Google Scholar
  4. 4.
    Brekelmans, J.: Brekel Kinect (2011), (online; accessed 2014)
  5. 5.
    Buttussi, F., Chittaro, L.: Mopet: A context-aware and user-adaptive wearable system for fitness training. Artificial Intelligence in Medicine 42(2), 153–163 (2008)CrossRefGoogle Scholar
  6. 6.
    Buttussi, F., Chittaro, L., Ranon, R., Verona, A.: Adaptation of graphics and gameplay in fitness games by exploiting motion and physiological sensors. In: Butz, A., Fisher, B., Krüger, A., Olivier, P., Owada, S. (eds.) SG 2007. LNCS, vol. 4569, pp. 85–96. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  7. 7.
    Dasgupta, A., Nakamura, Y.: Making feasible walking motion of humanoid robots from human motion capture data. In: IEEE International Conference on Robotics and Automation, vol. 2, pp. 1044–1049 (1999)Google Scholar
  8. 8.
    Delson, N., West, H.: Robot programming by human demonstration: Adaptation and inconsistency in constrained motion. In: IEEE International Conference on Robotics and Automation, vol. 1, pp. 30–36 (1996)Google Scholar
  9. 9.
    Fernández de Dios, P., Chung, P.W., Meng, Q.: Landmark-based methods for temporal alignment of human motions. IEEE Computational Intelligence Magazine 9(2), 29–37 (2014)CrossRefGoogle Scholar
  10. 10.
    Fernández de Dios, P., Meng, Q., Chung, P.W.: A machine learning method for identification of key body poses in cyclic physical exercises. In: IEEE International Conference on Systems, Man and Cybernetics (SMC), pp. 1605–1610 (October 2013)Google Scholar
  11. 11.
    Fox, J., Bailenson, J.N.: Virtual self-modeling: The effects of vicarious reinforcement and identification on exercise behaviors. Media Psychology 12(1), 1–25 (2009)CrossRefGoogle Scholar
  12. 12.
    Gleicher, M.: Retargetting motion to new characters. In: Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques, pp. 33–42. ACM (1998)Google Scholar
  13. 13.
    Kim, S.K., Chun, J., Park, H., Kwon, D., Ro, Y.: Interfacing sensors and virtual world health avatar application. In: 5th IEEE International Conference on New Trends in Information Science and Service Science (NISS), vol. 1, pp. 21–25 (2011)Google Scholar
  14. 14.
    Klaassen, R., Lavrysen, T., Geleijnse, G., van Halteren, A., Schwietert, H., van der Hout, M., et al.: A personal context-aware multi-device coaching service that supports a healthy lifestyle. In: 25th BCS Conference on Human-Computer Interaction, pp. 443–448 (2011)Google Scholar
  15. 15.
    Kurillo, G., Han, J.J., Nicorici, A., Bajcsy, R.: Tele-mfast: Kinect-based tele-medicine tool for remote motion and function assessment. In: Medicine Meets Virtual Reality 21: NextMed/MMVR21, vol. 196, p. 215 (2014)Google Scholar
  16. 16.
    Lisetti, C., Nasoz, F., LeRouge, C., Ozyer, O., Alvarez, K.: Developing multimodal intelligent affective interfaces for tele-home health care. International Journal of Human-Computer Studies 59(1), 245–255 (2003)CrossRefGoogle Scholar
  17. 17.
    Obdrzalek, S., Kurillo, G., Ofli, F., Bajcsy, R., Seto, E., Jimison, H., Pavel, M.: Accuracy and robustness of kinect pose estimation in the context of coaching of elderly population. In: 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 1188–1193. IEEE (2012)Google Scholar
  18. 18.
    Pirovano, M., Mainetti, R., Baud-Bovy, G., Lanzi, P.L., Borghese, N.A.: Self-adaptive games for rehabilitation at home. In: IEEE Conference on Computational Intelligence and Games (CIG), pp. 179–186 (2012)Google Scholar
  19. 19.
    Wieringa, W., op den Akker, H., Jones, V.M., op den Akker, R., Hermens, H.J.: Ontology-based generation of dynamic feedback on physical activity. In: Peleg, M., Lavrač, N., Combi, C. (eds.) AIME 2011. LNCS, vol. 6747, pp. 55–59. Springer, Heidelberg (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Pablo Fernández de Dios
    • 1
    Email author
  • Paul Wai Hing Chung
    • 1
  • Qinggang Meng
    • 1
  1. 1.Department of Computer ScienceLoughborough UniversityLoughboroughUK

Personalised recommendations