Multimedia Tools and Applications

, Volume 78, Issue 5, pp 5621–5643 | Cite as

Frame–based classification for cross-speed gait recognition

  • Jure Kovač
  • Vitomir Štruc
  • Peter PeerEmail author


The use of human gait as the means of biometric identification has gained a lot of attention in the past few years, mostly due to its enormous potential. Such biometrics can be captured at public places from a distance without subjects collaboration, awareness and even consent. However, there are still numerous challenges caused by influence of covariate factors like changes of walking speed, view, clothing, footwear etc., that have negative impact on recognition performance. In this paper we tackle walking speed changes with a skeleton model-based gait recognition system focusing on improving algorithm robustness and improving the performance at higher walking speed changes. We achieve these by proposing frame based classification method, which overcomes the main shortcoming of distance based classification methods, which are very sensitive to gait cycle starting point detection. The proposed technique is starting point invariant with respect to gait cycle starts and as such ensures independence of classification from gait cycle start positions. Additionally, we propose wavelet transform based signal approximation, which enables the analysis of feature signals on different frequency space resolutions and diminishes the need for using feature transformation that require training. With the evaluation on OU-ISIR gait dataset we demonstrate state of the art performance of proposed methods.


Biometric identification Computer vision Gait recognition Walking speed invariance 



Research was partly financed by the European Union, European Social Fund. This research was supported in parts also by the ARRS (Slovenian Research Agency) Research Program P2-0214 (A) Computer Vision and the ARRS Research Program P2-0250 (B) Metrology and Biometric Systems.

Compliance with Ethical Standards

Conflict of interests

The authors declare that they have no conflict of interest.


  1. 1.
    Alotaibi M, Mahmood A (2015) Improved gait recognition based on specialized deep convolutional neural networks. In: Applied Imagery Pattern Recognition Workshop. IEEE, pp 1–7.
  2. 2.
    Ariyanto G, Nixon MS (2012) Marionette mass-spring model for 3d gait biometrics. In: Biometrics. IEEE, New Delhi, pp 354–359.
  3. 3.
    Aung M, Thies S, Kenney L, Howard D, Selles R, Findlow A, Goulermas J Automated detection of instantaneous gait events using time frequency analysis and manifold embedding. Trans Neural Syst Rehabil Eng 21(6). CrossRefGoogle Scholar
  4. 4.
    Castro F, Marin-Jimenez M, Guil N, de la Blanca NP Automatic learning of gait signatures for people identification. arXiv:1603.01006
  5. 5.
    Iwashita Y, Sakano H, Kurazume R (2015) Gait recognition robust to speed transition using mutual subspace method. In: Image Analysis and Processing, Vol. 9279 of Lecture Notes in Computer Science. Springer, Berlin, pp 141–149. CrossRefGoogle Scholar
  6. 6.
    Jeevan M, Hanmandlu M, Panigrahi BK (2016) Information set based gait authentication system. Neurocomputing 207(C):1–14Google Scholar
  7. 7.
    Johansson G (1976) Visual motion perception. Sci Am 232(6):76–88. CrossRefGoogle Scholar
  8. 8.
    Kobayashi T, Otsu N (2008) Three-way auto-correlation approach to motion recognition. Pattern Recogn Lett 30(3):212–221CrossRefGoogle Scholar
  9. 9.
    Kovač J, Peer P (2013) Transformation based walking speed normalization for gait recognition. KSII Trans Internet Inf Syst 7(11):2690–2701CrossRefGoogle Scholar
  10. 10.
    Kovač J, Peer P (2014) Human skeleton model based dynamic features for walking speed invariant gait recognition. Math Probl Eng 2014:1–15. CrossRefGoogle Scholar
  11. 11.
    Kusakunniran W (2014) Attribute-based learning for gait recognition using spatio-temporal interest points. Image Vis Comput 32 (12):1117–1126. CrossRefGoogle Scholar
  12. 12.
    Kusakunniran W, Wu Q, Zhang J, Li H (2011) Speed-invariant gait recognition based on procrustes shape analysis using higher-order shape configuration. In: Image Processing. IEEE, pp 545–548.
  13. 13.
    Kusakunniran W, Wu Q, Zhang J, Li H (2012) Differential composition model. Syst Man Cybern 42(6):1654–1668CrossRefGoogle Scholar
  14. 14.
    Lee S, Collins R (2007) Shape variation-based frieze pattern for robust gait recognition. In: Computer Vision and Pattern Recognition. IEEE, pp 1–8.
  15. 15.
    Li W, Kuo CCJ, Peng J Gait recognition via gei subspace projections and collaborative representation classification, NeurocomputingGoogle Scholar
  16. 16.
    Liu Z, Sarkar S (2004) Simplest representation yet for gait recognition: averaged silhouette. In: International Conference on Pattern Recognition, vol 4. IEEE, pp 211–214.
  17. 17.
    Liu Z, Sarkar S (2006) Improved gait recognition by gait dynamics normalization. IEEE Trans Pattern Anal Mach Intell 28(6):863–76CrossRefGoogle Scholar
  18. 18.
    Lu H, Plataniotis K, Venetsanopoulos A (2008) A full-body layered deformable model for automatic model-based gait recognition. J Advan Signal Process 2008:1–14. CrossRefzbMATHGoogle Scholar
  19. 19.
    Makihara Y, Mannami H, Tsuji A, Hossain MA, Sugiura K, Mori A, Yagi Y (2012) The OU-ISIR gait database comprising the treadmill dataset. Trans Comput Vision Appl 4:53–62Google Scholar
  20. 20.
    Peternel M, Leonardis A (2004) Visual learning and recognition of a probabilistic spatio-temporal model of cyclic human locomotion. In: International Conference on Pattern Recognition, vol 4. IEEE, pp 146–149.
  21. 21.
    Rahati S, Moravejian R, Kazemi FM (2008) Gait recognition using wavelet transform. In: International Conference on Information Technology: New Generations. IEEE, pp 932–936.
  22. 22.
    Sarkar S, Phillips PJ, Liu Z, Vega IR, Grother P, Bowyer KW (2005) The humanID gait challenge problem: data sets, performance, and analysis. IEEE Trans Pattern Anal Mach Intell 27(2):162–177. CrossRefGoogle Scholar
  23. 23.
    Tan D, Huang K, Yu S, Tan T (2006) Efficient night gait recognition based on template matching. In: International Conference on Pattern Recognition. IEEE, pp 1000–1003.
  24. 24.
    Tanawongsuwan R, Bobick A (2004) Modelling the effects of walking speed on appearance-based gait recognition. In: Computer Vision and Pattern Recognition, vol 2. IEEE, pp 783–790.
  25. 25.
    Tsuji A, Makihara Y, Yagi Y (2010) Silhouette transformation based on walking speed for gait identification. In: International Conference on Computer Vision and Pattern Recognition, pp 717– 722Google Scholar
  26. 26.
    Valcik J, Sedmidubsky J, Zezula P Assessing similarity models for human-motion retrieval applications, Computer Animation and Virtual Worlds. CrossRefGoogle Scholar
  27. 27.
    Veeraraghavan A, Srivastava A, Roy-Chowdhury AK, Chellappa R (2009) Rate-invariant recognition of humans and their activities. Trans Image Process 18 (6):1326–39MathSciNetCrossRefGoogle Scholar
  28. 28.
    Xue Z, Ming D, Song W, Wan B, Jin S (2010) Infrared gait recognition based on wavelet transform and support vector machine. Pattern Recogn 43(8):2904–2910. CrossRefGoogle Scholar
  29. 29.
    Yoo J, Nixon MS (2011) Automated markerless analysis of human gait motion for recognition and classification. ETRI J Inf Telecommun Electron 33(2):259–266Google Scholar
  30. 30.
    Yu T, Zou JH (2012) Automatic human gait imitation and recognition in 3d from monocular video with an uncalibrated camera. Math Probl Eng 2012:1–35MathSciNetzbMATHGoogle Scholar
  31. 31.
    Zhang C, Liu W, Ma H, Fu H (2016) Siamese neural network based gait recognition for human identification. In: International Conference on Acoustics, Speech and Signal Processing. IEEE, pp 2832–2836.

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2017

Authors and Affiliations

  1. 1.Faculty of Computer and Information ScienceUniversity of LjubljanaLjubljanaSlovenia
  2. 2.Faculty of Electrical EngineeringUniversity of LjubljanaLjubljanaSlovenia

Personalised recommendations