Advertisement

Multi-layer Perceptron Architecture for Kinect-Based Gait Recognition

  • A. S. M. Hossain BariEmail author
  • Marina L. Gavrilova
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11542)

Abstract

Accurate gait recognition is of high significance for numerous industrial and consumer applications, including virtual reality, online games, medical rehabilitation, video surveillance, and others. This paper proposes multi-layer perceptron (MLP) based neural network architecture for human gait recognition. Two unique geometric features: joint relative cosine dissimilarity (JRCD) and joint relative triangle area (JRTA) are introduced. These features are view and pose invariant, and thus enhance recognition performance. MLP model is trained using dynamic JRTA and JRCD sequences. The performance of the proposed MLP architecture is evaluated on publicly available 3D Kinect skeleton gait database and is shown to be superior to other state-of-the-art methods.

Keywords

Gait recognition Human motion Joint relative triangle area Joint relative cosine dissimilarity Neural network Biometrics 

Notes

Acknowledgments

Authors would like to acknowledge partial support from NSERC DG “Machine Intelligence for Biometric Security”, NSERC ENGAGE on Gait Recognition and NSERC SPG on Smart Cities funding.

References

  1. 1.
    Ahmed, F., Paul, P.P., Gavrilova, M.L.: DTW-based kernel and rank-level fusion for 3D gait recognition using kinect. Vis. Comput. 31(6–8), 915–924 (2015)CrossRefGoogle Scholar
  2. 2.
    Andersson, V.O., de Araújo, R.M.: Person identification using anthropometric and gait data from kinect sensor. In: AAAI, pp. 425–431 (2015)Google Scholar
  3. 3.
    Ball, A., Rye, D., Ramos, F., Velonaki, M.: Unsupervised clustering of people from ‘skeleton’ data. In: ACM/IEEE HRI, pp. 225–226. ACM (2012)Google Scholar
  4. 4.
    Dikovski, B., Madjarov, G., Gjorgjevikj, D.: Evaluation of different feature sets for gait recognition using skeletal data from kinect. In: Information and Communication Technology, Electronics and Microelectronics, pp. 1304–1308. IEEE (2014)Google Scholar
  5. 5.
    Gavrilova, M.L., Wang, Y., Ahmed, F., Paul, P.P.: Kinect sensor gesture and activity recognition: new applications for consumer cognitive systems. IEEE Consum. Electron. Mag. 7(1), 88–94 (2018)CrossRefGoogle Scholar
  6. 6.
    Han, J., Bhanu, B.: Individual recognition using gait energy image. IEEE Trans. Pattern Anal. Mach. Intell. 2, 316–322 (2006)CrossRefGoogle Scholar
  7. 7.
    Han, J., Bhanu, B.: Statistical feature fusion for gait-based human recognition. In: CVPR 2004, vol. 2, p. 2. IEEE (2004)Google Scholar
  8. 8.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)Google Scholar
  9. 9.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167 (2015)
  10. 10.
    Kastaniotis, D., Theodorakopoulos, I., Theoharatos, C., Economou, G., Fotopoulos, S.: A framework for gait-based recognition using kinect. Pattern Recogn. Lett. 68, 327–335 (2015)CrossRefGoogle Scholar
  11. 11.
    Maret, Y., Oberson, D., Gavrilova, M.: Identifying an emotional state from body movements using genetic-based algorithms. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds.) ICAISC 2018. LNCS (LNAI), vol. 10841, pp. 474–485. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-91253-0_44CrossRefGoogle Scholar
  12. 12.
    Popa, M., Kemal Koc, A., Rothkrantz, L.J.M., Shan, C., Wiggers, P.: Kinect sensing of shopping related actions. In: Wichert, R., Van Laerhoven, K., Gelissen, J. (eds.) AmI 2011. CCIS, vol. 277, pp. 91–100. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-31479-7_16CrossRefGoogle Scholar
  13. 13.
    Preis, J., Kessel, M., Werner, M., Linnhoff-Popien, C.: Gait recognition with kinect. In: International Workshop on Kinect in Pervasive Computing, New Castle, UK, pp. 1–4 (2012)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.University of CalgaryCalgaryCanada

Personalised recommendations