Frontal-Standing Pose Based Person Identification Using Kinect

  • Kingshuk Chakravarty
  • Tanushyam Chattopadhyay
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8511)


In this paper we propose a person identification methodology from frontal standing posture using only skeleton information obtained from Kinect. In the first stage, features related to the physical characteristic of a person are calculated for every frame and then noisy frames are removed based on these features using unsupervised learning based approach. We have also proposed 6 new angle and area related features along with the physical build of a person for the supervised learning based identification. Experimental results indicate that the proposed algorithm is able to achieve 96% recognition accuracy and outperforms all the stat-of-the-art methods suggested by Sinha et al. and Preis et al.


Support Vector Machine Structural Risk Minimization Gait Recognition Multiclass Support Vector Machine Distance Base Outlier 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Preis, J., Kessel, M., Werner, M., Linnhoff-Popien, C.: Gait recognition with kinect. In: 1st International Workshop on Kinect in Pervasive Computing (2012)Google Scholar
  2. 2.
    Ball, A., Rye, D., Ramos, F., Velonaki, M.: Unsupervised clustering of people from skeleton data. In: 2012 7th ACM/IEEE International Conference on Human-Robot Interaction (HRI), pp. 225–226. IEEE (2012)Google Scholar
  3. 3.
    Kumar, M., Babu, R.V.: Human gait recognition using depth camera: a covariance based approach. In: Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing, p. 20. ACM (2012)Google Scholar
  4. 4.
    Sinha, A., Chakravarty, K.: Pose based person identification using kinect. In: 2013 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 497–503. IEEE (2013)Google Scholar
  5. 5.
    Microsoft: Kinect SDK (2012), (accessed February 6, 2014)
  6. 6.
    Arthur, D., Vassilvitskii, S.: k-means++: The advantages of careful seeding. In: Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, Society for Industrial and Applied Mathematics, pp. 1027–1035 (2007)Google Scholar
  7. 7.
    Mohri, M., Afshin Rostamizadeh, A.T.: Foundations of Machine Learning. The MIT Press (2012)Google Scholar
  8. 8.
    Wikipedia: Supervised learning — wikipedia, the free encyclopedia, (accessed February 6, 2014)
  9. 9.
    Vapnik, V.N.: The nature of statistical learning theory. Statistics for engineering and information science. Springer, Berlin (1999)Google Scholar
  10. 10.
    Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning 20(3), 273–297 (1995)zbMATHGoogle Scholar
  11. 11.
    Cortes, C., Vapnik, N.V.: Support-vector networks. Machine Learning, 20Google Scholar
  12. 12.
    Wikipedia: Support vector machine — wikipedia, the free encyclopedia, (accessed February 6, 2014)
  13. 13.
    Aizerman, M.A., Braverman, E.M.: Rozonoer: Theoretical foundations of the potential function method in pattern recognition learning. Automation and Remote Control 25, 821–837 (1964)MathSciNetGoogle Scholar
  14. 14.
    Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: Proceedings of the Fifth Annual Workshop on Computational Learning Theory. ACM (1992)Google Scholar
  15. 15.
    Platt, J.C., Cristianini, N., Shawe-taylor, J.: Large margin dags for multiclass classification. Advances in Neural Information Processing Systems 12(3), 547–553 (2000)Google Scholar
  16. 16.
    Dietterich, T.G., Bakiri, G.: Solving multiclass learning problems via error-correcting output codes. Journal of Artificial Intelligence Research 2, 263–286 (1995)zbMATHGoogle Scholar
  17. 17.
    Newcombe, R.A., et al.: Kinectfusion: Real-time dense surface mapping and tracking. In: 2011 10th IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 127–136. IEEE (2011)Google Scholar
  18. 18.
    Sinha, A., Chakravarty, K., Bhowmick, B.: Person identification using skeleton information from kinect. In: ACHI 2013, The Sixth International Conference on Advances in Computer-Human Interactions, pp. 101–108 (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Kingshuk Chakravarty
    • 1
  • Tanushyam Chattopadhyay
    • 1
  1. 1.Innovation LabTata Consultancy Services Ltd.KolkataIndia

Personalised recommendations